+# coding: utf-8
from __future__ import unicode_literals
import re
int_or_none,
js_to_json,
limit_length,
+ parse_count,
sanitized_Request,
try_get,
urlencode_postdata,
_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'
+ _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true&payloadtype=primary'
_TESTS = [{
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'uploader': 'Tennis on Facebook',
'upload_date': '20140908',
'timestamp': 1410199200,
- }
+ },
+ 'skip': 'Requires logging in',
}, {
- 'note': 'Video without discernible title',
'url': 'https://www.facebook.com/video.php?v=274175099429670',
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
- 'title': 'Asif Nawab Butt posted a video to his Timeline.',
+ 'title': 're:^Asif Nawab Butt posted a video',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
+ 'thumbnail': r're:^https?://.*',
},
'expected_warnings': [
'title'
'upload_date': '20160110',
'timestamp': 1452431627,
},
+ 'skip': 'Requires logging in',
}, {
'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
'info_dict': {
'id': '10153664894881749',
'ext': 'mp4',
- 'title': 'Facebook video #10153664894881749',
+ 'title': 'Average time to confirm recent Supreme Court nominees: 67 days Longest it\'s t...',
+ 'thumbnail': r're:^https?://.*',
+ 'timestamp': 1456259628,
+ 'upload_date': '20160223',
+ 'uploader': 'Barack Obama',
},
}, {
# have 1080P, but only up to 720p in swf params
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
- 'md5': '0d9813160b146b3bc8744e006027fcc6',
+ 'md5': '9571fae53d4165bbbadb17a94651dcdc',
'info_dict': {
'id': '10155529876156509',
'ext': 'mp4',
- 'title': 'Holocaust survivor becomes US citizen',
+ 'title': 'She survived the holocaust — and years later, she’s getting her citizenship s...',
'timestamp': 1477818095,
'upload_date': '20161030',
'uploader': 'CNN',
+ 'thumbnail': r're:^https?://.*',
+ 'view_count': int,
+ },
+ }, {
+ # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
+ 'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
+ 'info_dict': {
+ 'id': '1417995061575415',
+ 'ext': 'mp4',
+ 'title': 'md5:1db063d6a8c13faa8da727817339c857',
+ 'timestamp': 1486648217,
+ 'upload_date': '20170209',
+ 'uploader': 'Yaroslav Korpan',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
+ 'info_dict': {
+ 'id': '1072691702860471',
+ 'ext': 'mp4',
+ 'title': 'md5:ae2d22a93fbb12dad20dc393a869739d',
+ 'timestamp': 1477305000,
+ 'upload_date': '20161024',
+ 'uploader': 'La Guía Del Varón',
+ 'thumbnail': r're:^https?://.*',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/',
+ 'info_dict': {
+ 'id': '1396382447100162',
+ 'ext': 'mp4',
+ 'title': 'md5:19a428bbde91364e3de815383b54a235',
+ 'timestamp': 1486035494,
+ 'upload_date': '20170202',
+ 'uploader': 'Elisabeth Ahtn',
+ },
+ 'params': {
+ 'skip_download': True,
},
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
}, {
'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670',
'only_matching': True,
+ }, {
+ # no title
+ 'url': 'https://www.facebook.com/onlycleverentertainment/videos/1947995502095005/',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.facebook.com/WatchESLOne/videos/359649331226507/',
+ 'info_dict': {
+ 'id': '359649331226507',
+ 'ext': 'mp4',
+ 'title': '#ESLOne VoD - Birmingham Finals Day#1 Fnatic vs. @Evil Geniuses',
+ 'uploader': 'ESL One Dota 2',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}]
@staticmethod
- def _extract_url(webpage):
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
- if mobj is not None:
- return mobj.group('url')
-
+ def _extract_urls(webpage):
+ urls = []
+ for mobj in re.finditer(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
+ webpage):
+ urls.append(mobj.group('url'))
# Facebook API embed
# see https://developers.facebook.com/docs/plugins/embedded-video-player
-
mobj = re.search(r'''(?x)<div[^>]+
+
for mobj in re.finditer(r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
- data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage)
- if mobj is not None:
- return mobj.group('url')
+ data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage):
+ urls.append(mobj.group('url'))
+ return urls
def _login(self):
- (useremail, password) = self._get_login_info()
+ useremail, password = self._get_login_info()
if useremail is None:
return
for item in instances:
if item[1][0] == 'VideoConfig':
video_item = item[2][0]
- if video_item.get('video_id') == video_id:
+ if video_item.get('video_id'):
return video_item['videoData']
server_js_data = self._parse_json(self._search_regex(
if server_js_data:
video_data = extract_video_data(server_js_data.get('instances', []))
+ def extract_from_jsmods_instances(js_data):
+ if js_data:
+ return extract_video_data(try_get(
+ js_data, lambda x: x['jsmods']['instances'], list) or [])
+
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
- r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet',
+ r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_\d+)',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
- if server_js_data:
- video_data = extract_video_data(try_get(
- server_js_data, lambda x: x['jsmods']['instances'],
- list) or [])
+ video_data = extract_from_jsmods_instances(server_js_data)
if not video_data:
if not fatal_if_no_video:
expected=True)
elif '>You must log in to continue' in webpage:
self.raise_login_required()
- else:
- raise ExtractorError('Cannot parse data')
+ # Video info not in first request, do a secondary request using
+ # tahoe player specific URL
+ tahoe_data = self._download_webpage(
+ self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id,
+ data=urlencode_postdata({
+ '__a': 1,
+ '__pc': self._search_regex(
+ r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage,
+ 'pkg cohort', default='PHASED:DEFAULT'),
+ '__rev': self._search_regex(
+ r'client_revision["\']\s*:\s*(\d+),', webpage,
+ 'client revision', default='3944515'),
+ 'fb_dtsg': self._search_regex(
+ r'"DTSGInitialData"\s*,\s*\[\]\s*,\s*{\s*"token"\s*:\s*"([^"]+)"',
+ webpage, 'dtsg token', default=''),
+ }),
+ headers={
+ 'Content-Type': 'application/x-www-form-urlencoded',
+ })
+ tahoe_js_data = self._parse_json(
+ self._search_regex(
+ r'for\s+\(\s*;\s*;\s*\)\s*;(.+)', tahoe_data,
+ 'tahoe js data', default='{}'),
+ video_id, fatal=False)
+ video_data = extract_from_jsmods_instances(tahoe_js_data)
+
+ if not video_data:
+ raise ExtractorError('Cannot parse data')
+
+ subtitles = {}
formats = []
for f in video_data:
format_id = f['stream_type']
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
+ subtitles_src = f[0].get('subtitles_src')
+ if subtitles_src:
+ subtitles.setdefault('en', []).append({'url': subtitles_src})
if not formats:
raise ExtractorError('Cannot find video formats')
+ # Downloads with browser's User-Agent are rate limited. Working around
+ # with non-browser User-Agent.
+ for f in formats:
+ f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1'
+
self._sort_formats(formats)
video_title = self._html_search_regex(
- r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
- default=None)
+ r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage,
+ 'title', default=None)
if not video_title:
video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
webpage, 'alternative title', default=None)
if not video_title:
video_title = self._html_search_meta(
- 'description', webpage, 'title')
+ 'description', webpage, 'title', default=None)
if video_title:
video_title = limit_length(video_title, 80)
else:
video_title = 'Facebook video #%s' % video_id
uploader = clean_html(get_element_by_id(
'fbPhotoPageAuthorName', webpage)) or self._search_regex(
- r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
+ r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader',
+ default=None) or self._og_search_title(webpage, fatal=False)
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))
+ thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
+
+ view_count = parse_count(self._search_regex(
+ r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
+ default=None))
info_dict = {
'id': video_id,
'formats': formats,
'uploader': uploader,
'timestamp': timestamp,
+ 'thumbnail': thumbnail,
+ 'view_count': view_count,
+ 'subtitles': subtitles,
}
return webpage, info_dict
Rapsys Git / youtubedl / blobdiff