R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #344 from aviperes/bugfix_facebook_unavilable_video

Browse Source 
Bugfix facebook unavilable video
This commit is contained in:
aviperetz34 2020-06-29 09:40:21 +03:00 committed by GitHub
commit 9e7bad18d9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 43 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
test/ci/test_facebook.py
View File

@ -1,5 +1,6 @@
import unittest
import youtube_dl
from youtube_dl.utils import DownloadError
class facebookMetaData(unittest.TestCase):
@ -25,8 +26,15 @@ class facebookMetaData(unittest.TestCase):
info = ydl.extract_info(url, download=False)
self.assertGreater(info.get('comment_count'), 0)
def test_meta_data(self):
params = {}
url = "https://www.facebook.com/parapsychological.centr/videos/177407933624543/"
ydl = youtube_dl.YoutubeDL(params)
info = ydl.extract_info(url, download=False)
self.assertGreater(info.get('comment_count'), 0)
def test_metadata_fetch_with_log_in(self):
url = "https://www.facebook.com/SerieA/videos/282581803097269"
url = "https://www.facebook.com/oristandup/videos/675360549895283"
params = {}
with open("cookie_file") as file:
proxy = "ec2-3-221-82-67.compute-1.amazonaws.com:3128"
@ -34,6 +42,8 @@ class facebookMetaData(unittest.TestCase):
params['proxy'] = proxy
ydl = youtube_dl.YoutubeDL(params)
info = ydl.extract_info(url, download=False)
print (info.get('title'))
print (info.get('timestamp'))
self.assertTrue(info.get('timestamp'))
self.assertTrue(info.get('view_count'))
self.assertTrue(info.get('comment_count'))
@ -41,6 +51,19 @@ class facebookMetaData(unittest.TestCase):
self.assertTrue(info.get('uploader_id'))
self.assertTrue(info.get('thumbnail'))
def test_unavailable_video(self):
url = "https://www.facebook.com/101457238278830/videos/287839102599521/"
params = {}
with open("cookie_file") as file:
try:
proxy = "ec2-3-221-82-67.compute-1.amazonaws.com:3128"
params['cookiefile'] = file.name
params['proxy'] = proxy
ydl = youtube_dl.YoutubeDL(params)
info = ydl.extract_info(url, download=False)
except DownloadError:
self.assertRaises(DownloadError)
if __name__ == '__main__':
unittest.main()

28
youtube_dl/extractor/facebook.py
View File

@ -374,13 +374,7 @@ class FacebookIE(InfoExtractor):
if not video_data:
if not fatal_if_no_video:
return webpage, False
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None:
raise ExtractorError(
'The video is not available, Facebook said: "%s"' % m_msg.group(1),
expected=True)
elif '>You must log in to continue' in webpage:
self.raise_login_required()
self.validate_webpage(webpage)
if not video_data:
info_dict = self.get_from_new_ui(webpage, tahoe_data, video_id)
@ -806,13 +800,29 @@ class FacebookIE(InfoExtractor):
def _resolve_thumbnail(self, webpage, tahoe_data):
thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
if not thumbnail:
thumbnail = self._search_regex(r'"thumbSrc":"(.+?)"', tahoe_data.secondary, 'thumbnail', fatal=False)
thumbnail = self._search_regex(r'"thumbnailUrl":"(.+?)"', webpage, 'thumbnail', fatal=False)
thumbnail = str(thumbnail).replace('\\', "")
return thumbnail
def _valid_video_title(self, video_title):
return video_title and not u'Log In or Sign Up to View' in video_title
if video_title:
video_title = video_title.lower()
return video_title and not u'log in or sign up to view' in video_title
def validate_webpage(self, webpage):
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None:
raise ExtractorError(
'The video is not available, Facebook said: "%s"' % m_msg.group(1),
expected=True)
if 'Your Request Couldn\'t be Processed' in webpage:
raise ExtractorError(
'The video is not available, Facebook said: this content is not available',
expected=True)
elif '>You must log in to continue' in webpage:
self.raise_login_required()
class FacebookTahoeData: