aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--youtube_dl/extractor/cspan.py13
-rw-r--r--youtube_dl/extractor/facebook.py20
2 files changed, 25 insertions, 8 deletions
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index 7b685d157..b3ee67018 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -58,18 +58,23 @@ class CSpanIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
+ video_type = None
webpage = self._download_webpage(url, video_id)
- matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
- if matches:
+ # We first look for clipid, because clipprog always appears before
+ patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
+ results = list(filter(None, (re.search(p, webpage) for p in patterns)))
+ if results:
+ matches = results[0]
video_type, video_id = matches.groups()
- if video_type == 'prog':
- video_type = 'program'
+ video_type = 'clip' if video_type == 'id' else 'program'
else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
title = self._og_search_title(webpage)
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
+ if video_type is None or video_id is None:
+ raise ExtractorError('unable to find video id and type')
def get_text_attr(d, attr):
return d.get(attr, {}).get('#text')
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 39c481068..5e43f2359 100644
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -74,7 +74,7 @@ class FacebookIE(InfoExtractor):
return
login_page_req = sanitized_Request(self._LOGIN_URL)
- login_page_req.add_header('Cookie', 'locale=en_US')
+ self._set_cookie('facebook.com', 'locale', 'en_US')
login_page = self._download_webpage(login_page_req, None,
note='Downloading login page',
errnote='Unable to download login page')
@@ -100,13 +100,25 @@ class FacebookIE(InfoExtractor):
login_results = self._download_webpage(request, None,
note='Logging in', errnote='unable to fetch login page')
if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
+ 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)
self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return
+ 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 = {
- 'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
- 'h': self._search_regex(
- r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
+ 'fb_dtsg': fb_dtsg,
+ 'h': h,
'name_action_selected': 'dont_save',
}
check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))