From c8b9c6fd413a859ee702ef4cb43632491a097ec3 Mon Sep 17 00:00:00 2001 From: Arjun Sreedharan Date: Tue, 11 Feb 2014 13:25:24 +0530 Subject: [PATCH 1/3] use unicode_literals --- youtube_dl/extractor/yahoo.py | 60 ++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 29 deletions(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index e17a39782..d92d14f71 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import itertools import json import re @@ -12,25 +14,25 @@ from ..utils import ( class YahooIE(InfoExtractor): - IE_DESC = u'Yahoo screen' + IE_DESC = 'Yahoo screen' _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P\d*?)\.html' _TESTS = [ { - u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - u'file': u'214727115.mp4', - u'md5': u'4962b075c08be8690a922ee026d05e69', - u'info_dict': { - u'title': u'Julian Smith & Travis Legg Watch Julian Smith', - u'description': u'Julian and Travis watch Julian Smith', + 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', + 'file': '214727115.mp4', + 'md5': '4962b075c08be8690a922ee026d05e69', + 'info_dict': { + 'title': 'Julian Smith & Travis Legg Watch Julian Smith', + 'description': 'Julian and Travis watch Julian Smith', }, }, { - u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - u'file': u'103000935.mp4', - u'md5': u'd6e6fc6e1313c608f316ddad7b82b306', - u'info_dict': { - u'title': u'Codefellas - The Cougar Lies with Spanish Moss', - u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', + 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', + 'file': '103000935.mp4', + 'md5': 'd6e6fc6e1313c608f316ddad7b82b306', + 'info_dict': { + 'title': 'Codefellas - The Cougar Lies with Spanish Moss', + 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', }, }, ] @@ -41,7 +43,7 @@ class YahooIE(InfoExtractor): webpage = self._download_webpage(url, video_id) items_json = self._search_regex(r'mediaItems: ({.*?})$', - webpage, u'items', flags=re.MULTILINE) + webpage, 'items', flags=re.MULTILINE) items = json.loads(items_json) info = items['mediaItems']['query']['results']['mediaObj'][0] # The 'meta' field is not always in the video webpage, we request it @@ -60,7 +62,7 @@ class YahooIE(InfoExtractor): }) query_result_json = self._download_webpage( 'http://video.query.yahoo.com/v1/public/yql?' + data, - video_id, u'Downloading video info') + video_id, 'Downloading video info') query_result = json.loads(query_result_json) info = query_result['query']['results']['mediaObj'][0] meta = info['meta'] @@ -103,13 +105,13 @@ class YahooNewsIE(YahooIE): _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P\d*?)\.html' _TEST = { - u'url': u'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', - u'md5': u'67010fdf3a08d290e060a4dd96baa07b', - u'info_dict': { - u'id': u'104538833', - u'ext': u'mp4', - u'title': u'China Moses Is Crazy About the Blues', - u'description': u'md5:9900ab8cd5808175c7b3fe55b979bed0', + 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + 'md5': '67010fdf3a08d290e060a4dd96baa07b', + 'info_dict': { + 'id': '104538833', + 'ext': 'mp4', + 'title': 'China Moses Is Crazy About the Blues', + 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', }, } @@ -120,14 +122,14 @@ class YahooNewsIE(YahooIE): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, u'long id') + long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id') return self._get_info(long_id, video_id) class YahooSearchIE(SearchInfoExtractor): - IE_DESC = u'Yahoo screen search' + IE_DESC = 'Yahoo screen search' _MAX_RESULTS = 1000 - IE_NAME = u'screen.yahoo:search' + IE_NAME = 'screen.yahoo:search' _SEARCH_KEY = 'yvsearch' def _get_n_results(self, query, n): @@ -139,12 +141,12 @@ class YahooSearchIE(SearchInfoExtractor): 'entries': [] } for pagenum in itertools.count(0): - result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) + result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) webpage = self._download_webpage(result_url, query, note='Downloading results page '+str(pagenum+1)) info = json.loads(webpage) - m = info[u'm'] - results = info[u'results'] + m = info['m'] + results = info['results'] for (i, r) in enumerate(results): if (pagenum * 30) +i >= n: @@ -152,7 +154,7 @@ class YahooSearchIE(SearchInfoExtractor): mobj = re.search(r'(?Pscreen\.yahoo\.com/.*?-\d*?\.html)"', r) e = self.url_result('http://' + mobj.group('url'), 'Yahoo') res['entries'].append(e) - if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)): + if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)): break return res From c361e394e5a2b81a725518fa32adddea638e53b6 Mon Sep 17 00:00:00 2001 From: Arjun Sreedharan Date: Tue, 11 Feb 2014 13:26:34 +0530 Subject: [PATCH 2/3] use unicode_literals --- youtube_dl/extractor/xvideos.py | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 90138d7e5..2ab6d9704 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -9,12 +11,12 @@ from ..utils import ( class XVideosIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' _TEST = { - u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1', - u'file': u'939581.flv', - u'md5': u'1d0c835822f0a71a7bf011855db929d0', - u'info_dict': { - u"title": u"Funny Porns By >>>>S<<<<<< -1", - u"age_limit": 18, + 'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1', + 'file': '939581.flv', + 'md5': '1d0c835822f0a71a7bf011855db929d0', + 'info_dict': { + "title": "Funny Porns By >>>>S<<<<<< -1", + "age_limit": 18, } } @@ -28,15 +30,15 @@ class XVideosIE(InfoExtractor): # Extract video URL video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&', - webpage, u'video URL')) + webpage, 'video URL')) # Extract title video_title = self._html_search_regex(r'(.*?)\s+-\s+XVID', - webpage, u'title') + webpage, 'title') # Extract video thumbnail video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', - webpage, u'thumbnail', fatal=False) + webpage, 'thumbnail', fatal=False) info = { 'id': video_id, From 84c3fc26e8f29bd42d9472cc6e4ac4ca2be81563 Mon Sep 17 00:00:00 2001 From: Arjun Sreedharan <arjun024@gmail.com> Date: Tue, 11 Feb 2014 13:27:49 +0530 Subject: [PATCH 3/3] use unicode_literals --- youtube_dl/extractor/xtube.py | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 1a6a7688d..8f8001b4c 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -10,14 +12,14 @@ from ..utils import ( class XTubeIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))' _TEST = { - u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_', - u'file': u'kVTUy_G222_.mp4', - u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab', - u'info_dict': { - u"title": u"strange erotica", - u"description": u"surreal gay themed erotica...almost an ET kind of thing", - u"uploader": u"greenshowers", - u"age_limit": 18, + 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', + 'file': 'kVTUy_G222_.mp4', + 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', + 'info_dict': { + "title": "strange erotica", + "description": "surreal gay themed erotica...almost an ET kind of thing", + "uploader": "greenshowers", + "age_limit": 18, } } @@ -30,10 +32,10 @@ class XTubeIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title') - video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False) - video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', fatal=False) - video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/') + video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, 'title') + video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_", "([^"]+)', webpage, 'uploader', fatal=False) + video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, 'description', fatal=False) + video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, 'video_url').replace('\\/', '/') path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2]