yt-dlc/youtube_dl/extractor/facebook.py

191 lines
7.8 KiB
Python
Raw Normal View History

2014-03-04 03:36:54 +01:00
from __future__ import unicode_literals
2013-06-23 20:59:45 +02:00
import json
import re
import socket
from .common import InfoExtractor
from ..compat import (
2013-06-23 20:59:45 +02:00
compat_http_client,
compat_urllib_error,
compat_urllib_parse_unquote,
)
from ..utils import (
error_to_compat_str,
2013-06-23 20:59:45 +02:00
ExtractorError,
limit_length,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
sanitized_Request,
urlencode_postdata,
2015-08-02 23:52:12 +02:00
get_element_by_id,
clean_html,
2013-06-23 20:59:45 +02:00
)
class FacebookIE(InfoExtractor):
_VALID_URL = r'''(?x)
2014-03-09 18:42:44 +01:00
https?://(?:\w+\.)?facebook\.com/
(?:[^#]*?\#!/)?
2015-04-16 18:08:52 +02:00
(?:
(?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
(?:v|video_id)=|
[^/]+/videos/(?:[^/]+/)?
2015-04-16 18:08:52 +02:00
)
(?P<id>[0-9]+)
(?:.*)'''
_LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
_CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
2013-06-23 20:59:45 +02:00
_NETRC_MACHINE = 'facebook'
2014-03-04 03:36:54 +01:00
IE_NAME = 'facebook'
2014-08-27 11:08:47 +02:00
_TESTS = [{
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'md5': '6a40d33c0eccbb1af76cf0485a052659',
2014-03-04 03:36:54 +01:00
'info_dict': {
'id': '637842556329505',
2014-03-04 03:36:54 +01:00
'ext': 'mp4',
2014-09-29 05:19:56 +02:00
'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
'uploader': 'Tennis on Facebook',
2013-06-27 20:46:46 +02:00
}
}, {
'note': 'Video without discernible title',
'url': 'https://www.facebook.com/video.php?v=274175099429670',
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
'title': 'Facebook video #274175099429670',
'uploader': 'Asif Nawab Butt',
},
'expected_warnings': [
'title'
]
2014-08-27 11:08:47 +02:00
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
'only_matching': True,
2015-04-16 18:08:52 +02:00
}, {
'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
'only_matching': True,
}, {
'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
'only_matching': True,
2014-08-27 11:08:47 +02:00
}]
2013-06-23 20:59:45 +02:00
def _login(self):
(useremail, password) = self._get_login_info()
2013-06-23 20:59:45 +02:00
if useremail is None:
return
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
login_page_req = sanitized_Request(self._LOGIN_URL)
2015-12-28 16:37:02 +01:00
self._set_cookie('facebook.com', 'locale', 'en_US')
login_page = self._download_webpage(login_page_req, None,
2014-11-23 21:39:15 +01:00
note='Downloading login page',
errnote='Unable to download login page')
2014-03-04 03:39:04 +01:00
lsd = self._search_regex(
2014-03-04 03:39:45 +01:00
r'<input type="hidden" name="lsd" value="([^"]*)"',
2014-03-04 03:39:04 +01:00
login_page, 'lsd')
2014-03-04 03:36:54 +01:00
lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd')
2013-06-23 20:59:45 +02:00
login_form = {
'email': useremail,
'pass': password,
'lsd': lsd,
'lgnrnd': lgnrnd,
'next': 'http://facebook.com/home.php',
'default_persistent': '0',
'legacy_return': '1',
'timezone': '-60',
'trynum': '1',
2014-11-23 22:21:46 +01:00
}
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
2013-06-23 20:59:45 +02:00
try:
login_results = self._download_webpage(request, None,
2014-11-23 21:39:15 +01:00
note='Logging in', errnote='unable to fetch login page')
2013-06-23 20:59:45 +02:00
if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
2015-12-28 16:20:09 +01:00
error = self._html_search_regex(
r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>',
login_results, 'login error', default=None, group='error')
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
2016-01-10 16:17:47 +01:00
self._downloader.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.')
2013-06-23 20:59:45 +02:00
return
2015-12-28 16:37:02 +01:00
fb_dtsg = self._search_regex(
r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None)
h = self._search_regex(
r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None)
if not fb_dtsg or not h:
return
check_form = {
2015-12-28 16:37:02 +01:00
'fb_dtsg': fb_dtsg,
'h': h,
'name_action_selected': 'dont_save',
}
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
check_response = self._download_webpage(check_req, None,
2014-11-23 21:39:15 +01:00
note='Confirming login')
if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
2016-01-10 16:17:47 +01:00
self._downloader.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.')
2013-06-23 20:59:45 +02:00
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err))
2013-06-23 20:59:45 +02:00
return
def _real_initialize(self):
self._login()
2013-06-23 20:59:45 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2013-06-23 20:59:45 +02:00
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
webpage = self._download_webpage(url, video_id)
BEFORE = '{swf.addParam(param[0], param[1]);});\n'
AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
if not m:
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None:
raise ExtractorError(
2014-03-04 03:36:54 +01:00
'The video is not available, Facebook said: "%s"' % m_msg.group(1),
expected=True)
else:
2014-03-04 03:36:54 +01:00
raise ExtractorError('Cannot parse data')
2013-06-23 20:59:45 +02:00
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
2013-06-23 20:59:45 +02:00
params = json.loads(params_raw)
formats = []
for format_id, f in params['video_data'].items():
if not f or not isinstance(f, list):
continue
for quality in ('sd', 'hd'):
for src_type in ('src', 'src_no_ratelimit'):
src = f[0].get('%s_%s' % (quality, src_type))
if src:
formats.append({
'format_id': '%s_%s_%s' % (format_id, quality, src_type),
'url': src,
'preference': -10 if format_id == 'progressive' else 0,
})
if not formats:
raise ExtractorError('Cannot find video formats')
2013-06-23 20:59:45 +02:00
video_title = self._html_search_regex(
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)
video_title = limit_length(video_title, 80)
if not video_title:
video_title = 'Facebook video #%s' % video_id
2015-08-02 23:52:12 +02:00
uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
2013-06-23 20:59:45 +02:00
2014-03-09 18:42:44 +01:00
return {
2013-06-23 20:59:45 +02:00
'id': video_id,
'title': video_title,
'formats': formats,
2015-08-02 23:52:12 +02:00
'uploader': uploader,
2013-06-23 20:59:45 +02:00
}