From a5155b4ea631ed823afbde3e5eb14fa389320375 Mon Sep 17 00:00:00 2001 From: Dawid Cywka Date: Mon, 28 Dec 2015 00:55:38 -0500 Subject: [PATCH 1/2] [vimeo] support private videos in password-protected albums (fixes #8030) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vimeo.py | 59 ++++++++++++++++++++++++++++---- 2 files changed, 53 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c1dbf9f21..0e16f9f9a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -778,6 +778,7 @@ from .viidea import ViideaIE from .vimeo import ( VimeoIE, VimeoAlbumIE, + VimeoAlbumVideoIE, VimeoChannelIE, VimeoGroupsIE, VimeoLikesIE, diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index ce08e6955..6cef776b9 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -237,7 +237,7 @@ class VimeoIE(VimeoBaseInfoExtractor): if url.startswith('http://'): # vimeo only supports https now, but the user can give an http url url = url.replace('http://', 'https://') - password_request = sanitized_Request(url + '/password', data) + password_request = sanitized_Request(url, data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') password_request.add_header('Referer', url) self._set_vimeo_cookie('vuid', vuid) @@ -261,6 +261,15 @@ class VimeoIE(VimeoBaseInfoExtractor): def _real_initialize(self): self._login() + def _extract_download_urls(self, mobj): + video_id = mobj.group('id') + if mobj.group('pro') or mobj.group('player'): + url = 'https://player.vimeo.com/video/' + video_id + else: + url = 'https://vimeo.com/' + video_id + json_url = 'https://vimeo.com/%s?action=load_download_config' % video_id + return url, json_url + def _real_extract(self, url): url, data = unsmuggle_url(url) headers = std_headers @@ -274,10 +283,7 @@ class VimeoIE(VimeoBaseInfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') orig_url = url - if mobj.group('pro') or mobj.group('player'): - url = 'https://player.vimeo.com/video/' + video_id - else: - url = 'https://vimeo.com/' + video_id + url, json_url = self._extract_download_urls(mobj) # Retrieve video webpage to extract further information request = sanitized_Request(url, None, headers) @@ -407,7 +413,7 @@ class VimeoIE(VimeoBaseInfoExtractor): comment_count = None formats = [] - download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={ + download_request = sanitized_Request(json_url, headers={ 'X-Requested-With': 'XMLHttpRequest'}) download_data = self._download_json(download_request, video_id, fatal=False) if download_data: @@ -472,6 +478,28 @@ class VimeoIE(VimeoBaseInfoExtractor): } +class VimeoAlbumVideoIE(VimeoIE): + _VALID_URL = r'''(?x) + https?:// + (?:(?:www|(?Pplayer))\.)? + vimeo(?Ppro)?\.com/ + album/(?P[0-9]+)/video/ + (?P[0-9]+) + /?(?:[?&].*)?(?:[#].*)?$''' + IE_NAME = 'vimeo:album_video' + _TESTS = [] + + def _extract_download_urls(self, mobj): + video_id = mobj.group('id') + list_id = mobj.group('list_id') + if mobj.group('pro') or mobj.group('player'): + url = 'https://player.vimeo.com/video/' + video_id + else: + url = 'https://vimeo.com/album/' + list_id + '/video/' + video_id + json_url = 'https://vimeo.com/album/%s/video/%s?action=load_download_config' % (list_id, video_id) + return url, json_url + + class VimeoChannelIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:channel' _VALID_URL = r'https://vimeo\.com/channels/(?P[^/?#]+)/?(?:$|[?#])' @@ -569,7 +597,7 @@ class VimeoUserIE(VimeoChannelIE): 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'
\n\s*

(.*?)

' _TESTS = [{ 'url': 'https://vimeo.com/album/2632481', @@ -598,6 +626,23 @@ class VimeoAlbumIE(VimeoChannelIE): album_id = self._match_id(url) return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) + def _title_and_entries(self, list_id, base_url): + for pagenum in itertools.count(1): + page_url = self._page_url(base_url, pagenum) + webpage = self._download_webpage( + page_url, list_id, + 'Downloading page %s' % pagenum) + + if pagenum == 1: + webpage = self._login_list_password(page_url, list_id, webpage) + yield self._extract_list_title(webpage) + + for video_id in re.findall(r'id="clip_(\d+?)"', webpage): + yield self.url_result('https://vimeo.com/album/%s/video/%s' % (list_id, video_id), 'VimeoAlbumVideo') + + if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: + break + class VimeoGroupsIE(VimeoAlbumIE): IE_NAME = 'vimeo:group' From ff7625298bce255ce5d1f2d8bf80dbb83d5c93f8 Mon Sep 17 00:00:00 2001 From: Dawid Cywka Date: Mon, 28 Dec 2015 14:19:51 -0500 Subject: [PATCH 2/2] [vimeo] test for private video in password-protected album --- youtube_dl/extractor/vimeo.py | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 6cef776b9..35e2a607b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -487,7 +487,22 @@ class VimeoAlbumVideoIE(VimeoIE): (?P[0-9]+) /?(?:[?&].*)?(?:[#].*)?$''' IE_NAME = 'vimeo:album_video' - _TESTS = [] + _TESTS = [{ + 'url': 'https://vimeo.com/album/3717291/video/150187356', + 'note': 'Private (only me) video in password-protected album', + 'info_dict': { + 'id': '150187356', + 'ext': 'mp4', + 'title': 'bbb sunflower 1080p 60fps normal', + 'upload_date': '20151228', + 'uploader_id': 'user31929058', + 'uploader': 'dcywka', + 'description': 'Blender Foundation | blender.org', + }, + 'params': { + 'videopassword': 'youtube-dl', + } + }] def _extract_download_urls(self, mobj): video_id = mobj.group('id') @@ -617,6 +632,17 @@ class VimeoAlbumIE(VimeoChannelIE): 'params': { 'videopassword': 'youtube-dl', } + }, { + 'note': 'Password-protected album with private video', + 'url': 'https://vimeo.com/album/3717291', + 'info_dict': { + 'title': 'youtube-dl test private album', + 'id': '3717291', + }, + 'playlist_count': 1, + 'params': { + 'videopassword': 'youtube-dl', + } }] def _page_url(self, base_url, pagenum):