Skip to content

Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
graceannmad merged 3 commits into from
Aug 11, 2025
Merged

Grace #44

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b58c760
working on RSS feed error checking -- taking a break for NER pipeline
graceannmad Aug 11, 2025
fdcc8d3
Merge branch 'development' into Grace
graceannmad Aug 11, 2025
1779dd9
NER works
graceannmad Aug 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 8 additions & 3 deletions src/ingest/ap_ingestor.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
try:
with sync_playwright() as p:
browser = p.chromium.launch(headless=True)
page = browser.new_page()
context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
viewport={"width": 1280, "height": 800})
page = context.new_page()

# browser = p.chromium.launch(headless=True)
# page = browser.new_page()

#change the article_url to the redirected one (or just the same)
article_url = self.resolve_google_news_redirect(article_url)
#print(article_url)
page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

# Wait for the main article body to load
page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
return full_text.strip()

except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
print(f"Playwright error fetching {article_url}: {e}")
return ""

13 changes: 4 additions & 9 deletions src/ingest/base_ingestor.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
)

for entry in feed.entries:
# print("\n--- ENTRY ---")
# for k, v in entry.items():
# print(f"{k}: {v}")
# print(entry.link)
formattedEntry = self.format_entry(entry)
save_entry(formattedEntry, using_celery)

def check_no_save_new_entries(self):
feed = feedparser.parse(self.RSS_URL)
all_entries = []

for entry in feed.entries:
all_entries.append(self.format_entry(entry))

return all_entries
14 changes: 12 additions & 2 deletions src/ingest/bbc_ingestor.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
soup = BeautifulSoup(response.content, 'html.parser')

article = soup.find('article')

if not article:
return None

if article:
return(article.get_text())
# # Remove unwanted sections like "related content", "media", or "byline"
# for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
# unwanted.decompose()

# Gather all paragraphs that are part of the article body
paragraphs = article.find_all('p')

cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
return cleaned_text
1 change: 1 addition & 0 deletions src/ingest/cnn_ingestor.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
# This RSS feed is from 2023????????

def fetch_full_text(self, url):
try:
Expand Down
4 changes: 4 additions & 0 deletions src/ingest/save_to_database.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

#dont save entries without body text
if entry["full_text"] == "" or entry["full_text"] == None:
print("Unable to fetch full text.")
return

#check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
current_app.tasks[ner_task.name]
#TODO: The following line can be used when connected to EC2 to actually use a GPU
#ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
print("Checkpoint 1")
ner_task.apply_async(args=[str(inserted_id)])
except NotRegistered:
# fallback to inline
print("Checkpoint 2")
ner_task(str(inserted_id))
else:
# Inline execution
print("Checkpoint 3")
ner_task(str(inserted_id))
16 changes: 10 additions & 6 deletions src/justinsight/celery.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
# "args": (),
# },

# NOT SAVING ANYTHING? WHAT HAPPENED
# Maybe we should just give up on getting AP to work...
# "check-APfeed-every-5-minutes": {
# "task": "justinsight.tasks.apLogger_task",
# "schedule": 5.0,
# "args": (),
# },

# "check-BBCfeed-every-5-minutes": {
# "task": "justinsight.tasks.bbcLogger_task",
# "schedule": 5.0,
# "args": (),
# },
# Checked and good
"check-BBCfeed-every-5-minutes": {
"task": "justinsight.tasks.bbcLogger_task",
"schedule": 5.0,
"args": (),
},

# Checked and good
# "check-CBSfeed-every-5-minutes": {
# "task": "justinsight.tasks.cbsLogger_task",
# "schedule": 5.0,
# "args": (),
# },

# Could not find a current RSS feed for CNN :(
# "check-CNNfeed-every-5-minutes": {
# "task": "justinsight.tasks.cnnLogger_task",
# "schedule": 5.0,
# "args": (),
# },

#I am here
# "check-LATIMESfeed-every-5-minutes": {
# "task": "justinsight.tasks.latimesLogger_task",
# "schedule": 5.0,
Expand Down
24 changes: 0 additions & 24 deletions src/justinsight/nlpthings.py
View file
Open in desktop

This file was deleted.

6 changes: 3 additions & 3 deletions src/justinsight/streamlitapp.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
# st.markdown(f"### Entry {i+1}")
# st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
st.markdown(f"### Entry {i+1}")
st.write(row.to_dict())



10 changes: 0 additions & 10 deletions src/justinsight/tasks.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
print(f"New worker so we can use GPU on this entry id: {entry_id}")
dummy_addToEntryInDB(entry_id)
#Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
# Process article with NER results
Expand Down
2 changes: 1 addition & 1 deletion src/nlp/ner_core.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
def __init__(self):
print("constructing NER Core instance")
print(" NER Core instance constructing")
super().__init__(
task="ner",
model_name="dslim/bert-base-NER",
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
Grace by graceannmad · Pull Request #44 · JustInternetAI/JustInsight · GitHub
Skip to content
Grace#44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

graceannmad
merged 3 commits into

from

Aug 11, 2025
 Merged


Grace
#44
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
b58c760

working on RSS feed error checking -- taking a break for NER pipeline


graceannmad Aug 11, 2025
fdcc8d3

Merge branch 'development' into Grace


graceannmad Aug 11, 2025
1779dd9

NER works


graceannmad Aug 11, 2025

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


11 changes: 8 additions & 3 deletions
src/ingest/ap_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -32,12 +32,17 @@ def fetch_full_text(self, article_url):
 try:
 with sync_playwright() as p:
 browser = p.chromium.launch(headless=True)
 page = browser.new_page()
 context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
 viewport={"width": 1280, "height": 800})
 page = context.new_page()

 # browser = p.chromium.launch(headless=True)
 # page = browser.new_page()

 #change the article_url to the redirected one (or just the same)
 article_url = self.resolve_google_news_redirect(article_url)
 #print(article_url)
 page.goto(article_url, wait_until="domcontentloaded", timeout=15000)
 page.goto(article_url, wait_until="domcontentloaded", timeout=30000)

 # Wait for the main article body to load
 page.wait_for_selector('div.RichTextStoryBody', timeout=3000)
Expand All@@ -50,6 +55,6 @@ def fetch_full_text(self, article_url):
 return full_text.strip()

 except Exception as e:
#print(f"Playwright error fetching {article_url}: {e}")
 print(f"Playwright error fetching {article_url}: {e}")
 return ""


13 changes: 4 additions & 9 deletions
src/ingest/base_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -46,14 +46,9 @@ def check_and_save_new_entries(self, using_celery=False):
 )

 for entry in feed.entries:
 # print("\n--- ENTRY ---")
 # for k, v in entry.items():
 # print(f"{k}: {v}")
 # print(entry.link)
 formattedEntry = self.format_entry(entry)
 save_entry(formattedEntry, using_celery)

 def check_no_save_new_entries(self):
 feed = feedparser.parse(self.RSS_URL)
 all_entries = []

 for entry in feed.entries:
 all_entries.append(self.format_entry(entry))

 return all_entries

14 changes: 12 additions & 2 deletions
src/ingest/bbc_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -10,6 +10,16 @@ def fetch_full_text(self, article_url):
 soup = BeautifulSoup(response.content, 'html.parser')

 article = soup.find('article')

 if not article:
 return None

 if article:
 return(article.get_text())
 # # Remove unwanted sections like "related content", "media", or "byline"
 # for unwanted in article.select('[data-component="byline"], [data-component="media-block"], .bbc-1msyfg1, .bbc-1fxtbkn'): # classes may vary
 # unwanted.decompose()

 # Gather all paragraphs that are part of the article body
 paragraphs = article.find_all('p')

 cleaned_text = '\n\n'.join(p.get_text(strip=True) for p in paragraphs)
 return cleaned_text

1 change: 1 addition & 0 deletions
src/ingest/cnn_ingestor.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@

class CNNIngestor(BaseIngestor):
 RSS_URL = "http://rss.cnn.com/rss/cnn_world.rss"
 # This RSS feed is from 2023????????

 def fetch_full_text(self, url):
 try:
Expand Down

4 changes: 4 additions & 0 deletions
src/ingest/save_to_database.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@ def save_entry(entry, using_celery):

 #dont save entries without body text
 if entry["full_text"] == "" or entry["full_text"] == None:
 print("Unable to fetch full text.")
 return

 #check if the entry has already been saved and if it has not then save it
Expand All@@ -34,10 +35,13 @@ def save_entry(entry, using_celery):
 current_app.tasks[ner_task.name]
 #TODO: The following line can be used when connected to EC2 to actually use a GPU
 #ner_task.apply_async(args=[str(inserted_id)], queue='gpu')
 print("Checkpoint 1")
 ner_task.apply_async(args=[str(inserted_id)])
 except NotRegistered:
 # fallback to inline
 print("Checkpoint 2")
 ner_task(str(inserted_id))
 else:
 # Inline execution
 print("Checkpoint 3")
 ner_task(str(inserted_id))

16 changes: 10 additions & 6 deletions
src/justinsight/celery.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,31 +16,35 @@
 # "args": (),
 # },

 # NOT SAVING ANYTHING? WHAT HAPPENED
 # Maybe we should just give up on getting AP to work...
 # "check-APfeed-every-5-minutes": {
 # "task": "justinsight.tasks.apLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # "check-BBCfeed-every-5-minutes": {
 # "task": "justinsight.tasks.bbcLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },
 # Checked and good 
 "check-BBCfeed-every-5-minutes": {
 "task": "justinsight.tasks.bbcLogger_task",
 "schedule": 5.0,
 "args": (),
 },

 # Checked and good
 # "check-CBSfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cbsLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 # Could not find a current RSS feed for CNN :(
 # "check-CNNfeed-every-5-minutes": {
 # "task": "justinsight.tasks.cnnLogger_task",
 # "schedule": 5.0,
 # "args": (),
 # },

 #I am here
 # "check-LATIMESfeed-every-5-minutes": {
 # "task": "justinsight.tasks.latimesLogger_task",
 # "schedule": 5.0,
Expand Down

24 changes: 0 additions & 24 deletions
src/justinsight/nlpthings.py

View file


Open in desktop


This file was deleted.


6 changes: 3 additions & 3 deletions
src/justinsight/streamlitapp.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,9 +28,9 @@
columns_to_show = st.multiselect("Columns to display", options=df.columns.tolist(), default=df.columns.tolist())
st.dataframe(df[columns_to_show])#, use_container_width=True)

# for i, row in df[columns_to_show].iterrows():
#  st.markdown(f"### Entry {i+1}")
#  st.write(row.to_dict())
for i, row in df[columns_to_show].iterrows():
 st.markdown(f"### Entry {i+1}")
 st.write(row.to_dict())




10 changes: 0 additions & 10 deletions
src/justinsight/tasks.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -8,10 +8,7 @@
from ingest.npr_ingestor import NPRIngestor
from ingest.nyt_ingestor import NYTIngestor
from ingest.usnews_ingestor import USNEWSIngestor
from .nlpthings import dummy_addToEntryInDB
from ingest.save_to_database import collection
from nlp.ner_core import NERCore
from bson import ObjectId

@shared_task
def sample_task():
Expand DownExpand Up@@ -80,13 +77,6 @@ def usnewsLogger_task():
 ingestor.check_and_save_new_entries(using_celery=True) # this will invoke the inherited logic
 return "USNEWS RSS Feed checked."


@shared_task
def runNER_task(entry_id):
 print(f"New worker so we can use GPU on this entry id: {entry_id}")
 dummy_addToEntryInDB(entry_id)
 #Do GPU-dependent processing here

@shared_task
def ner_task(article_id):
 # Process article with NER results
Expand Down

2 changes: 1 addition & 1 deletion
src/nlp/ner_core.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,7 +4,7 @@

class NERCore(BaseCore):
 def __init__(self):
 print("constructing NER Core instance")
 print(" NER Core instance constructing")
 super().__init__(
 task="ner",
 model_name="dslim/bert-base-NER",
Expand Down