compat_urllib_parse,
compat_urllib_request,
urlencode_postdata,
-
ExtractorError,
+ limit_length,
)
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<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'
_NETRC_MACHINE = 'facebook'
IE_NAME = 'facebook'
- _TEST = {
- 'url': 'https://www.facebook.com/photo.php?v=120708114770723',
- 'md5': '48975a41ccc4b7a581abd68651c1a5a8',
+ _TESTS = [{
+ 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
+ 'md5': '6a40d33c0eccbb1af76cf0485a052659',
'info_dict': {
- 'id': '120708114770723',
+ 'id': '637842556329505',
'ext': 'mp4',
- 'duration': 279,
- 'title': 'PEOPLE ARE AWESOME 2013'
+ 'duration': 38,
+ 'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...',
}
- }
-
- def report_login(self):
- """Report attempt to log in."""
- self.to_screen('Logging in')
+ }, {
+ 'note': 'Video without discernible title',
+ 'url': 'https://www.facebook.com/video.php?v=274175099429670',
+ 'info_dict': {
+ 'id': '274175099429670',
+ 'ext': 'mp4',
+ 'title': 'Facebook video #274175099429670',
+ }
+ }, {
+ 'url': 'https://www.facebook.com/video.php?v=10204634152394104',
+ 'only_matching': True,
+ }]
def _login(self):
(useremail, password) = self._get_login_info()
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"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
'name_action_selected': 'dont_save',
- 'submit[Continue]': self._search_regex(r'<button[^>]+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')
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
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'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title')
-
- info = {
+ r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
+ fatal=False)
+ 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
+
+ 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]