Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-12 14:26:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

[facebook] Support alternative webpage form

Browse Source 
Fixes #8371
This commit is contained in:
Yen Chi Hsuan 2016-01-30 19:30:39 +08:00
parent 7d106a65ca
commit c140629995
1 changed files with 24 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/facebook.py
View File

@ -150,10 +150,32 @@ def _real_extract(self, url):
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_data = None
BEFORE = '{swf.addParam(param[0], param[1]);});\n' BEFORE = '{swf.addParam(param[0], param[1]);});\n'
AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
if not m: if m:
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
video_data = json.loads(params_raw)['video_data']
def video_data_list2dict(video_data):
ret = {}
for item in video_data:
format_id = item['stream_type']
ret.setdefault(format_id, []).append(item)
return ret
if not video_data:
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id)
for item in server_js_data['instances']:
if item[1][0] == 'VideoConfig':
video_data = video_data_list2dict(item[2][0]['videoData'])
break
if not video_data:
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None: if m_msg is not None:
raise ExtractorError( raise ExtractorError(
@ -161,12 +183,9 @@ def _real_extract(self, url):
expected=True) expected=True)
else: else:
raise ExtractorError('Cannot parse data') raise ExtractorError('Cannot parse data')
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
params = json.loads(params_raw)
formats = [] formats = []
for format_id, f in params['video_data'].items(): for format_id, f in video_data.items():
if not f or not isinstance(f, list): if not f or not isinstance(f, list):
continue continue
for quality in ('sd', 'hd'): for quality in ('sd', 'hd'):