') + ')', '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('^' + ".*" + ', '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" + ', '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('^' + ".*" + ', '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); } })(); })(); GitHub - indictechcom/pywikisource: Wikisource Dedicated Python API library · GitHub
Skip to content

Latest commit

History

30 Commits

Folders and files

NameName
Last commit message
Last commit date

Repository files navigation

pywikisource

This library contains the basic API operations like

  • Number of Index Book
  • Current page quality status
  • Proofreader of page
  • Validator of page

It is wikisource dedicated API library.

Installation

  • pip install pywikisource

Demo 1

frompywikisourceimportWikiSourceApi# Create the Wikisource objectWS=WikiSourceApi('en')
# oruserAgent="MyCoolTool/1.1 (https://example.org/MyCoolTool/; MyCoolTool@example.org) pywikisource/0.0.4"WS=WikiSourceApi('en', userAgent) # It is recommended to add user agent.# Get page listpageList=WS.createdPageList('Landon in Literary Gazette 1833.pdf')
forpageinpageList:
print(page)
# Get the number of pages of Index Bookprint(WS.numpage('Landon in Literary Gazette 1833.pdf'))
# Get the proofreader of single pageprint(WS.proofreader('Page:Landon_in_Literary_Gazette_1833.pdf/3'))
# Get the validator of single pageprint(WS.validator('Page:Landon_in_Literary_Gazette_1833.pdf/3'))

Demo 2 (Async bookStatus; Since pywikisource 0.0.4)

frompywikisourceimportWikiSourceApiimportasynciouserAgent="MyCoolTool/1.1 (https://example.org/MyCoolTool/; MyCoolTool@example.org) pywikisource/0.0.4"WS=WikiSourceApi('ta', userAgent) # It is recommended to add user agent.books= [
"தமிழர் வரலாறு 1, பி. டி. சீனிவாச அய்யங்கார்.pdf",
"தமிழர் வரலாறு 2, பி. டி. சீனிவாச அய்யங்கார்.pdf",
"மாவீரர் மருதுபாண்டியர்.pdf",
"சேரன் செங்குட்டுவன்.djvu"
]
forbookinbooks:
pageList=WS.createdPageList( book )
# Default limit is 25 requests per seconddata=asyncio.run( WS.bookStatus( pageList, limit=50 ) )
fortitle, statusindata.items():
print( title, " --> ", status["code"] )

Author

Instruction for Maintainer

To deploy on PyPI

administrator@Jay-Prakash % python setup.py sdist bdist_wheel
administrator@Jay-Prakash % twine check dist/*
administrator@Jay-Prakash % twine upload dist/*

Licence

This is Free Software, released under the MIT.

About

Wikisource Dedicated Python API library

Resources

Stars

7 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages