X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fvimeo.py;h=28bcc89cd7423dafa40032076d1bd3ad12f4bdcf;hb=fec2d97ca2f1aa8b64c24b28d8c63cab052e9db4;hp=e7284049df7740b66d8e9462436de4593973bd87;hpb=a3fa5da4967bf2699bfd982cf56a8f627a13bda4;p=youtube-dl
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index e7284049d..28bcc89cd 100644
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -6,7 +6,6 @@ import re
import itertools
from .common import InfoExtractor
-from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse,
@@ -20,6 +19,7 @@ from ..utils import (
RegexNotFoundError,
smuggle_url,
std_headers,
+ unified_strdate,
unsmuggle_url,
urlencode_postdata,
)
@@ -38,7 +38,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
self.report_login()
login_url = 'https://vimeo.com/log_in'
webpage = self._download_webpage(login_url, None, False)
- token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+ token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token')
data = urlencode_postdata({
'email': username,
'password': password,
@@ -52,7 +52,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
self._download_webpage(login_request, None, False, 'Wrong login info')
-class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
+class VimeoIE(VimeoBaseInfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
@@ -140,6 +140,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
'description': 'md5:8678b246399b070816b12313e8b4eb5c',
'uploader_id': 'atencio',
'uploader': 'Peter Atencio',
+ 'upload_date': '20130927',
'duration': 187,
},
},
@@ -175,18 +176,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)
if password is None:
- raise ExtractorError('This video is protected by a password, use the --video-password option')
- token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
- data = compat_urllib_parse.urlencode({
+ raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
+ token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token')
+ data = urlencode_postdata({
'password': password,
'token': token,
})
- # I didn't manage to use the password with https
- if url.startswith('https'):
- pass_url = url.replace('https', 'http')
- else:
- pass_url = url
- password_request = compat_urllib_request.Request(pass_url + '/password', data)
+ if url.startswith('http://'):
+ # vimeo only supports https now, but the user can give an http url
+ url = url.replace('http://', 'https://')
+ password_request = compat_urllib_request.Request(url + '/password', data)
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
password_request.add_header('Cookie', 'xsrft=%s' % token)
return self._download_webpage(
@@ -223,7 +222,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
video_id = mobj.group('id')
orig_url = url
if mobj.group('pro') or mobj.group('player'):
- url = 'http://player.vimeo.com/video/' + video_id
+ url = 'https://player.vimeo.com/video/' + video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, headers)
@@ -245,6 +244,16 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
# and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
+ vimeo_config = self._search_regex(
+ r'vimeo\.config\s*=\s*({.+?});', webpage,
+ 'vimeo config', default=None)
+ if vimeo_config:
+ seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
+ if seed_status.get('state') == 'failed':
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, seed_status['title']),
+ expected=True)
+
# Extract the config JSON
try:
try:
@@ -318,9 +327,9 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
# Extract upload date
video_upload_date = None
- mobj = re.search(r'[^/?#]+)/?(?:$|[?#])'
+ _VALID_URL = r'https://vimeo\.com/channels/(?P[^/?#]+)/?(?:$|[?#])'
_MORE_PAGES_INDICATOR = r']+?title="(.*?)"'
_TESTS = [{
- 'url': 'http://vimeo.com/channels/tributes',
+ 'url': 'https://vimeo.com/channels/tributes',
'info_dict': {
'id': 'tributes',
'title': 'Vimeo Tributes',
@@ -432,10 +439,10 @@ class VimeoChannelIE(InfoExtractor):
name="([^"]+)"\s+
value="([^"]*)"
''', login_form))
- token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+ token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token')
fields['token'] = token
fields['password'] = password
- post = compat_urllib_parse.urlencode(fields)
+ post = urlencode_postdata(fields)
password_path = self._search_regex(
r'action="([^"]+)"', login_form, 'password URL')
password_url = compat_urlparse.urljoin(page_url, password_path)
@@ -462,7 +469,7 @@ class VimeoChannelIE(InfoExtractor):
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
- entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
+ entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
for video_id in video_ids]
return {'_type': 'playlist',
'id': list_id,
@@ -473,15 +480,15 @@ class VimeoChannelIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
- return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
+ return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
class VimeoUserIE(VimeoChannelIE):
IE_NAME = 'vimeo:user'
- _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P[^/]+)(?:/videos|[#?]|$)'
+ _VALID_URL = r'https://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P[^/]+)(?:/videos|[#?]|$)'
_TITLE_RE = r']+?class="user">([^<>]+?)'
_TESTS = [{
- 'url': 'http://vimeo.com/nkistudio/videos',
+ 'url': 'https://vimeo.com/nkistudio/videos',
'info_dict': {
'title': 'Nki',
'id': 'nkistudio',
@@ -492,15 +499,15 @@ class VimeoUserIE(VimeoChannelIE):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
- return self._extract_videos(name, 'http://vimeo.com/%s' % name)
+ return self._extract_videos(name, 'https://vimeo.com/%s' % name)
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = 'vimeo:album'
- _VALID_URL = r'https?://vimeo\.com/album/(?P\d+)'
+ _VALID_URL = r'https://vimeo\.com/album/(?P\d+)'
_TITLE_RE = r'