github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[facebook] Merge FacebookPostIE into FacebookIE

Browse source 
Fixes #8713
This commit is contained in:
Yen Chi Hsuan 2016-03-10 14:33:48 +08:00
parent e0dccdd398
commit 9c7b509b2a
2 changed files with 40 additions and 33 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/__init__.py
View file

@ -212,10 +212,7 @@
from .exfm import ExfmIE
from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE
from .facebook import (
FacebookIE,
FacebookPostIE,
)
from .facebook import FacebookIE
from .faz import FazIE
from .fc2 import FC2IE
from .fczenit import FczenitIE

56
youtube_dl/extractor/facebook.py
View file

@ -37,7 +37,8 @@ class FacebookIE(InfoExtractor):
video/embed|
story\.php
)\?(?:.*?)(?:v|video_id|story_fbid)=|
[^/]+/videos/(?:[^/]+/)?
[^/]+/videos/(?:[^/]+/)?|
[^/]+/posts/
)|
facebook:
)
@ -50,6 +51,8 @@ class FacebookIE(InfoExtractor):
_CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
_VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
_TESTS = [{
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'md5': '6a40d33c0eccbb1af76cf0485a052659',
@ -81,6 +84,15 @@ class FacebookIE(InfoExtractor):
'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
'uploader': 'Demy de Zeeuw',
},
}, {
'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',
}
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
'only_matching': True,
@ -164,9 +176,8 @@ def _login(self):
def _real_initialize(self):
self._login()
def _real_extract(self, url):
video_id = self._match_id(url)
req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
def _extract_from_url(self, url, video_id, fatal_if_no_video=True):
req = sanitized_Request(url)
req.add_header('User-Agent', self._CHROME_USER_AGENT)
webpage = self._download_webpage(req, video_id)
@ -196,6 +207,8 @@ def video_data_list2dict(video_data):
break
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(
@ -241,39 +254,36 @@ def video_data_list2dict(video_data):
video_title = 'Facebook video #%s' % video_id
uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
return {
info_dict = {
'id': video_id,
'title': video_title,
'formats': formats,
'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',
}
}
return webpage, info_dict
def _real_extract(self, url):
post_id = self._match_id(url)
video_id = self._match_id(url)
webpage = self._download_webpage(url, post_id)
real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url
webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False)
if info_dict:
return info_dict
if '/posts/' in url:
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)]
video_id)]
return self.playlist_result(entries, post_id)
return self.playlist_result(entries, video_id)
else:
_, info_dict = self._extract_from_url(
self._VIDEO_PAGE_TEMPLATE % video_id,
video_id, fatal_if_no_video=True)
return info_dict