mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-05-02 06:36:20 -04:00
monkey-patch youtube-dl to short-circuit
video extraction using generic extractor in case of very large url (more than 20 mb) that youtube-dl interprets as html, to avoid spinning forever here: Traceback (most recent call first): File "/opt/brozzler-ve3/lib/python3.5/re.py", line 213, in findall return _compile(pattern, flags).findall(string) File "/opt/brozzler-ve3/lib/python3.5/site-packages/youtube_dl/extractor/generic.py", line 2878, in _real_extract 'uploader': video_uploader, File "/opt/brozzler-ve3/lib/python3.5/site-packages/youtube_dl/extractor/common.py", line 503, in extract ie_result = self._real_extract(url) File "/opt/brozzler-ve3/lib/python3.5/site-packages/youtube_dl/YoutubeDL.py", line 792, in extract_info ie_result = ie.extract(url) File "/opt/brozzler-ve3/lib/python3.5/site-packages/brozzler/worker.py", line 302, in _try_youtube_dl info = ydl.extract_info(str(urlcanon.whatwg(page.url))) File "/opt/brozzler-ve3/lib/python3.5/site-packages/brozzler/worker.py", line 361, in brozzle_page self._try_youtube_dl(ydl, site, page)
This commit is contained in:
parent
b41ccd7e6b
commit
27bdfb65d2
2 changed files with 12 additions and 1 deletions
2
setup.py
2
setup.py
|
@ -32,7 +32,7 @@ def find_package_data(package):
|
|||
|
||||
setuptools.setup(
|
||||
name='brozzler',
|
||||
version='1.1b13.dev290',
|
||||
version='1.1b13.dev291',
|
||||
description='Distributed web crawling with browsers',
|
||||
url='https://github.com/internetarchive/brozzler',
|
||||
author='Noah Levitt',
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue