X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffacebook.py;h=1ad4e77a8a334dc0bfec62a0fb4752676e2e1435;hb=c4c5dc27cb6bd5bb091ea7ad73ba98f5a0324b90;hp=d675a939dda29f9faa620dea10641415553da1cf;hpb=50317dbbada099eaefdc4bc56fff8109907a827a;p=youtube-dl.git
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index d675a939d..1ad4e77a8 100644
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -5,15 +5,18 @@ import re
import socket
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_http_client,
compat_str,
compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
- urlencode_postdata,
-
+)
+from ..utils import (
ExtractorError,
+ int_or_none,
+ limit_length,
+ urlencode_postdata,
)
@@ -34,8 +37,15 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '637842556329505',
'ext': 'mp4',
- 'duration': 38,
- 'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...',
+ 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
+ }
+ }, {
+ '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',
@@ -50,8 +60,8 @@ class FacebookIE(InfoExtractor):
login_page_req = compat_urllib_request.Request(self._LOGIN_URL)
login_page_req.add_header('Cookie', 'locale=en_US')
login_page = self._download_webpage(login_page_req, None,
- note='Downloading login page',
- errnote='Unable to download login page')
+ note='Downloading login page',
+ errnote='Unable to download login page')
lsd = self._search_regex(
r'', login_results) is not None:
self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return
@@ -86,7 +96,7 @@ class FacebookIE(InfoExtractor):
check_req = compat_urllib_request.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,
- note='Confirming login')
+ note='Confirming login')
if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
@@ -97,9 +107,7 @@ class FacebookIE(InfoExtractor):
self._login()
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
webpage = self._download_webpage(url, video_id)
@@ -131,8 +139,7 @@ class FacebookIE(InfoExtractor):
video_title = self._html_search_regex(
r'(?s)(.*?)',
webpage, 'alternative title', default=None)
- if len(video_title) > 80 + 3:
- video_title = video_title[:80] + '...'
+ video_title = limit_length(video_title, 80)
if not video_title:
video_title = 'Facebook video #%s' % video_id
@@ -140,6 +147,6 @@ class FacebookIE(InfoExtractor):
'id': video_id,
'title': video_title,
'url': video_url,
- 'duration': int(video_data['video_duration']),
- 'thumbnail': video_data['thumbnail_src'],
+ 'duration': int_or_none(video_data.get('video_duration')),
+ 'thumbnail': video_data.get('thumbnail_src'),
}