EPF crawler, downloader and parser

pip install epf

Parser

importepf.parserfortableinepf.parser.parse('path/to/file.tbz'):
print(table)
column_names= [c[0] forcintable['columns']]
forrintable['record_generator']():
print(dict(zip(column_names, r)))

table=epf.parser.parse('path/to/table_file').next():
print(table)
column_names= [c[0] forcintable['columns']]
forrintable['record_generator']():
print(dict(zip(column_names, r)))

Crawler

importepf.crawlerimportrecrawl=lambdau, r, f=None, d=False: \
epf.crawler.crawl(url=u, auth=('user', 'pass'), recursive=r, filter_=f,
yield_dirs=d)
url=sorted(crawl(EPF_V4_FULL_URL, r=False, d=True))[-1]
assertre.match('^.*/\d{8}/$', url)
rx=re.compile('.*(itunes|incremental|application|popularity).*|^\d+/$')
f=lambdan: rx.match(n)
forlincrawl(url, r=True, f=f):
print(l)

Downloader

importepf.downloaderepf.downloader.download(tbz_url, tbz_path, auth=('user', 'pass'))

License: MIT