X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvimeo.py;h=4cd2f73d9962529db31e259011db9ccbfe053ac4;hb=62b013df0dcb5f902d745b77b3de62b64b828863;hp=e6a86f18ec5018615344e547cd332892c81fc665;hpb=72ebb5e4b4756a05f37ffcd0efaaf5c07ffc1fd1;p=youtube-dl.git diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index e6a86f18e..4cd2f73d9 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -4,20 +4,22 @@ from __future__ import unicode_literals import json import re import itertools +import hashlib from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( - clean_html, +from ..compat import ( compat_HTTPError, compat_urllib_parse, compat_urllib_request, compat_urlparse, +) +from ..utils import ( ExtractorError, - get_element_by_attribute, InAdvancePagedList, int_or_none, RegexNotFoundError, + smuggle_url, std_headers, unsmuggle_url, urlencode_postdata, @@ -157,12 +159,24 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'duration': 62, } }, + { + # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ + 'url': 'https://player.vimeo.com/video/98044508', + 'note': 'The js code contains assignments to the same variable as the config', + 'info_dict': { + 'id': '98044508', + 'ext': 'mp4', + 'title': 'Pier Solar OUYA Official Trailer', + 'uploader': 'Tulio Gonçalves', + 'uploader_id': 'user28849593', + }, + }, ] 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') + 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 = compat_urllib_parse.urlencode({ 'password': password, @@ -176,9 +190,9 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): password_request = compat_urllib_request.Request(pass_url + '/password', data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') password_request.add_header('Cookie', 'xsrft=%s' % token) - self._download_webpage(password_request, video_id, - 'Verifying the password', - 'Wrong password') + return self._download_webpage( + password_request, video_id, + 'Verifying the password', 'Wrong password') def _verify_player_video_password(self, url, video_id): password = self._downloader.params.get('videopassword', None) @@ -212,6 +226,11 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id + password = self._downloader.params.get('videopassword', None) + if password: + headers['Cookie'] = '%s_password=%s' % ( + video_id, hashlib.md5(password.encode('utf-8')).hexdigest()) + # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) try: @@ -244,19 +263,22 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # We try to find out to which variable is assigned the config dic m_variable_name = re.search('(\w)\.video\.id', webpage) if m_variable_name is not None: - config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1)) + config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) else: config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] config = self._search_regex(config_re, webpage, 'info section', - flags=re.DOTALL) + flags=re.DOTALL) config = json.loads(config) except Exception as e: if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') - if re.search(']+?id="pw_form"', webpage) is not None: + if re.search(r']+?id="pw_form"', webpage) is not None: + if data and '_video_password_verified' in data: + raise ExtractorError('video password verification failed!') self._verify_video_password(url, video_id, webpage) - return self._real_extract(url) + return self._real_extract( + smuggle_url(url, {'_video_password_verified': 'verified'})) else: raise ExtractorError('Unable to extract info section', cause=e) @@ -389,6 +411,7 @@ class VimeoChannelIE(InfoExtractor): _TESTS = [{ 'url': 'http://vimeo.com/channels/tributes', 'info_dict': { + 'id': 'tributes', 'title': 'Vimeo Tributes', }, 'playlist_mincount': 25, @@ -400,12 +423,47 @@ class VimeoChannelIE(InfoExtractor): def _extract_list_title(self, webpage): return self._html_search_regex(self._TITLE_RE, webpage, 'list title') + def _login_list_password(self, page_url, list_id, webpage): + login_form = self._search_regex( + r'(?s)]+?id="pw_form"(.*?)', + webpage, 'login form', default=None) + if not login_form: + return webpage + + password = self._downloader.params.get('videopassword', None) + if password is None: + raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) + fields = dict(re.findall(r'''(?x)[^/]+)' _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', - 'file': '75524534.mp4', 'md5': 'c507a72f780cacc12b2248bb4006d253', 'info_dict': { + 'id': '75524534', + 'ext': 'mp4', 'title': "DICK HARDWICK 'Comedian'", 'uploader': 'Richard Hardwick', } @@ -502,7 +574,7 @@ class VimeoReviewIE(InfoExtractor): 'info_dict': { 'id': '91613211', 'ext': 'mp4', - 'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn', + 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', 'uploader': 'DevWeek Events', 'duration': 2773, 'thumbnail': 're:^https?://.*\.jpg$', @@ -550,6 +622,7 @@ class VimeoLikesIE(InfoExtractor): 'url': 'https://vimeo.com/user755559/likes/', 'playlist_mincount': 293, "info_dict": { + 'id': 'user755559_likes', "description": "See all the videos urza likes", "title": 'Videos urza likes', },