From 9148eb002beecaadb69394bc4a779ee1c328142b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 6 Jan 2014 23:38:16 +0100 Subject: [PATCH] [vimeo] Use unicode_literals --- youtube_dl/extractor/vimeo.py | 117 +++++++++++++++++----------------- 1 file changed, 60 insertions(+), 57 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index d832e45d4..54b550b0c 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1,4 +1,6 @@ # encoding: utf-8 +from __future__ import unicode_literals + import json import re import itertools @@ -31,54 +33,55 @@ class VimeoIE(InfoExtractor): (?P[0-9]+) /?(?:[?&].*)?(?:[#].*)?$''' _NETRC_MACHINE = 'vimeo' - IE_NAME = u'vimeo' + IE_NAME = 'vimeo' _TESTS = [ { - u'url': u'http://vimeo.com/56015672#at=0', - u'file': u'56015672.mp4', - u'md5': u'8879b6cc097e987f02484baf890129e5', - u'info_dict': { - u"upload_date": u"20121220", - u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - u"uploader_id": u"user7108434", - u"uploader": u"Filippo Valsorda", - u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", + 'url': 'http://vimeo.com/56015672#at=0', + 'file': '56015672.mp4', + 'md5': '8879b6cc097e987f02484baf890129e5', + 'info_dict': { + "upload_date": "20121220", + "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", + "uploader_id": "user7108434", + "uploader": "Filippo Valsorda", + "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", }, }, { - u'url': u'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', - u'file': u'68093876.mp4', - u'md5': u'3b5ca6aa22b60dfeeadf50b72e44ed82', - u'note': u'Vimeo Pro video (#1197)', - u'info_dict': { - u'uploader_id': u'openstreetmapus', - u'uploader': u'OpenStreetMap US', - u'title': u'Andy Allan - Putting the Carto into OpenStreetMap Cartography', + 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', + 'file': '68093876.mp4', + 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', + 'note': 'Vimeo Pro video (#1197)', + 'info_dict': { + 'uploader_id': 'openstreetmapus', + 'uploader': 'OpenStreetMap US', + 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', }, }, { - u'url': u'http://player.vimeo.com/video/54469442', - u'file': u'54469442.mp4', - u'md5': u'619b811a4417aa4abe78dc653becf511', - u'note': u'Videos that embed the url in the player page', - u'info_dict': { - u'title': u'Kathy Sierra: Building the minimum Badass User, Business of Software', - u'uploader': u'The BLN & Business of Software', + 'url': 'http://player.vimeo.com/video/54469442', + 'file': '54469442.mp4', + 'md5': '619b811a4417aa4abe78dc653becf511', + 'note': 'Videos that embed the url in the player page', + 'info_dict': { + 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software', + 'uploader': 'The BLN & Business of Software', + 'uploader_id': 'theblnbusinessofsoftware', }, }, { - u'url': u'http://vimeo.com/68375962', - u'file': u'68375962.mp4', - u'md5': u'aaf896bdb7ddd6476df50007a0ac0ae7', - u'note': u'Video protected with password', - u'info_dict': { - u'title': u'youtube-dl password protected test video', - u'upload_date': u'20130614', - u'uploader_id': u'user18948128', - u'uploader': u'Jaime Marquínez Ferrándiz', + 'url': 'http://vimeo.com/68375962', + 'file': '68375962.mp4', + 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', + 'note': 'Video protected with password', + 'info_dict': { + 'title': 'youtube-dl password protected test video', + 'upload_date': '20130614', + 'uploader_id': 'user18948128', + 'uploader': 'Jaime Marquínez Ferrándiz', }, - u'params': { - u'videopassword': u'youtube-dl', + 'params': { + 'videopassword': 'youtube-dl', }, }, ] @@ -100,12 +103,12 @@ def _login(self): login_request = compat_urllib_request.Request(login_url, data) login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') login_request.add_header('Cookie', 'xsrft=%s' % token) - self._download_webpage(login_request, None, False, u'Wrong login info') + self._download_webpage(login_request, None, False, 'Wrong login info') def _verify_video_password(self, url, video_id, webpage): password = self._downloader.params.get('videopassword', None) if password is None: - raise ExtractorError(u'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') token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1) data = compat_urllib_parse.urlencode({'password': password, 'token': token}) @@ -118,8 +121,8 @@ def _verify_video_password(self, url, video_id, webpage): 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, - u'Verifying the password', - u'Wrong password') + 'Verifying the password', + 'Wrong password') def _real_initialize(self): self._login() @@ -134,7 +137,7 @@ def _real_extract(self, url): # Extract ID from URL mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) video_id = mobj.group('id') if mobj.group('pro') or mobj.group('player'): @@ -155,7 +158,7 @@ def _real_extract(self, url): try: try: config_url = self._html_search_regex( - r' data-config-url="(.+?)"', webpage, u'config URL') + r' data-config-url="(.+?)"', webpage, 'config URL') config_json = self._download_webpage(config_url, video_id) config = json.loads(config_json) except RegexNotFoundError: @@ -166,18 +169,18 @@ def _real_extract(self, url): 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, u'info section', + config = self._search_regex(config_re, webpage, 'info section', 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(u'The author has restricted the access to this video, try with the "--referer" option') + 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: self._verify_video_password(url, video_id, webpage) return self._real_extract(url) else: - raise ExtractorError(u'Unable to extract info section', + raise ExtractorError('Unable to extract info section', cause=e) else: if config.get('view') == 4: @@ -216,9 +219,9 @@ def _real_extract(self, url): video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) try: - view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, u'view count')) - like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, u'like count')) - comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, u'comment count')) + view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) + like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) + comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) except RegexNotFoundError: # This info is only available in vimeo.com/{id} urls view_count = None @@ -259,7 +262,7 @@ def _real_extract(self, url): for key in ('other', 'sd', 'hd'): formats += files[key] if len(formats) == 0: - raise ExtractorError(u'No known codec found') + raise ExtractorError('No known codec found') return { 'id': video_id, @@ -278,7 +281,7 @@ def _real_extract(self, url): class VimeoChannelIE(InfoExtractor): - IE_NAME = u'vimeo:channel' + IE_NAME = 'vimeo:channel' _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P[^/]+)' _MORE_PAGES_INDICATOR = r']+?title="(.*?)"' @@ -287,14 +290,14 @@ def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) def _extract_list_title(self, webpage): - return self._html_search_regex(self._TITLE_RE, webpage, u'list title') + return self._html_search_regex(self._TITLE_RE, webpage, 'list title') def _extract_videos(self, list_id, base_url): video_ids = [] for pagenum in itertools.count(1): webpage = self._download_webpage( self._page_url(base_url, pagenum) ,list_id, - u'Downloading page %s' % pagenum) + 'Downloading page %s' % pagenum) video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: break @@ -314,7 +317,7 @@ def _real_extract(self, url): class VimeoUserIE(VimeoChannelIE): - IE_NAME = u'vimeo:user' + IE_NAME = 'vimeo:user' _VALID_URL = r'(?:https?://)?vimeo.\com/(?P[^/]+)(?:[#?]|$)' _TITLE_RE = r']+?class="user">([^<>]+?)' @@ -331,7 +334,7 @@ def _real_extract(self, url): class VimeoAlbumIE(VimeoChannelIE): - IE_NAME = u'vimeo:album' + IE_NAME = 'vimeo:album' _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P\d+)' _TITLE_RE = r'