X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffacebook.py;h=574a8639021698d8b47fcb14b11d65c3a8818414;hb=f30a38be8b3c32500e168f93f68fc1f36a62b29d;hp=848a2c26373f3c28dd2736258500be8094e6b57a;hpb=b74fa8cd2c9deb412ac277c6cc44847c3839b844;p=youtube-dl diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 848a2c263..574a86390 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -18,32 +18,29 @@ from ..utils import ( class FacebookIE(InfoExtractor): - """Information Extractor for Facebook""" - _VALID_URL = r'''(?x) - (?:https?://)?(?:\w+\.)?facebook\.com/ - (?:[^#?]*\#!/)? - (?:video/video\.php|photo\.php|video/embed)\?(?:.*?) + https?://(?:\w+\.)?facebook\.com/ + (?:[^#]*?\#!/)? + (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?) (?:v|video_id)=(?P[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' _NETRC_MACHINE = 'facebook' IE_NAME = 'facebook' - _TEST = { + _TESTS = [{ 'url': 'https://www.facebook.com/photo.php?v=120708114770723', 'md5': '48975a41ccc4b7a581abd68651c1a5a8', 'info_dict': { 'id': '120708114770723', 'ext': 'mp4', 'duration': 279, - 'title': 'PEOPLE ARE AWESOME 2013' + 'title': 'PEOPLE ARE AWESOME 2013', } - } - - def report_login(self): - """Report attempt to log in.""" - self.to_screen('Logging in') + }, { + 'url': 'https://www.facebook.com/video.php?v=10204634152394104', + 'only_matching': True, + }] def _login(self): (useremail, password) = self._get_login_info() @@ -82,9 +79,8 @@ class FacebookIE(InfoExtractor): check_form = { 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'), - 'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, 'nh'), + 'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'), 'name_action_selected': 'dont_save', - 'submit[Continue]': self._search_regex(r']+value="(.*?)"[^>]+name="submit\[Continue\]"', login_results, 'continue'), } check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') @@ -101,8 +97,6 @@ class FacebookIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) video_id = mobj.group('id') url = 'https://www.facebook.com/video/video.php?v=%s' % video_id @@ -128,18 +122,14 @@ class FacebookIE(InfoExtractor): video_url = video_data['sd_src'] if not video_url: raise ExtractorError('Cannot find video URL') - video_duration = int(video_data['video_duration']) - thumbnail = video_data['thumbnail_src'] video_title = self._html_search_regex( r'

([^<]*)

', webpage, 'title') - info = { + return { 'id': video_id, 'title': video_title, 'url': video_url, - 'ext': 'mp4', - 'duration': video_duration, - 'thumbnail': thumbnail, + 'duration': int(video_data['video_duration']), + 'thumbnail': video_data['thumbnail_src'], } - return [info]