Browse Source

[facebook:post] Add extractor (Closes #8321)

master
Sergey M․ 8 years ago
parent
commit
de691a498d
2 changed files with 34 additions and 1 deletions
  1. 5
      youtube_dl/extractor/__init__.py
  2. 30
      youtube_dl/extractor/facebook.py

5
youtube_dl/extractor/__init__.py

@ -196,7 +196,10 @@ from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE from .exfm import ExfmIE
from .expotv import ExpoTVIE from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .facebook import (
FacebookIE,
FacebookPostIE,
)
from .faz import FazIE from .faz import FazIE
from .fc2 import FC2IE from .fc2 import FC2IE
from .fczenit import FczenitIE from .fczenit import FczenitIE

30
youtube_dl/extractor/facebook.py

@ -199,3 +199,33 @@ class FacebookIE(InfoExtractor):
'formats': formats, 'formats': formats,
'uploader': uploader, 'uploader': uploader,
} }
class FacebookPostIE(InfoExtractor):
IE_NAME = 'facebook:post'
_VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)'
_TEST = {
'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
'info_dict': {
'id': '544765982287235',
'ext': 'mp4',
'title': '"What are you doing running in the snow?"',
'uploader': 'FailArmy',
}
}
def _real_extract(self, url):
post_id = self._match_id(url)
webpage = self._download_webpage(url, post_id)
entries = [
self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
for video_id in self._parse_json(
self._search_regex(
r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
webpage, 'video ids', group='ids'),
post_id)]
return self.playlist_result(entries, post_id)
Loading…
Cancel
Save