From 5ee6fc974e617ce2f8d9d62c416091a1daa6d802 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 6 Mar 2015 02:43:05 +0800 Subject: [PATCH 1/5] [sohu] Fix info extractor and add tests --- youtube_dl/extractor/sohu.py | 46 +++++++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index c04791997..ef7ec51df 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -4,22 +4,42 @@ import re from .common import InfoExtractor -from .common import compat_str +from ..utils import compat_str +from ..compat import compat_urllib_request class SohuIE(InfoExtractor): _VALID_URL = r'https?://(?Pmy\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P\d+)\.shtml.*?' - _TEST = { + _TESTS = [{ + 'note': 'This video is available only in Mainland China', 'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super', - 'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7', + 'md5': '29175c8cadd8b5cc4055001e85d6b372', 'info_dict': { 'id': '382479172', 'ext': 'mp4', 'title': 'MV:Far East Movement《The Illest》', }, - 'skip': 'Only available from China', - } + 'params': { + 'cn_verification_proxy': 'proxy.uku.im:8888' + } + }, { + 'url': 'http://tv.sohu.com/20150305/n409385080.shtml', + 'md5': '699060e75cf58858dd47fb9c03c42cfb', + 'info_dict': { + 'id': '409385080', + 'ext': 'mp4', + 'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》', + } + }, { + 'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml', + 'md5': '9bf34be48f2f4dadcb226c74127e203c', + 'info_dict': { + 'id': '78693464', + 'ext': 'mp4', + 'title': '【爱范品】第31期:MWC见不到的奇葩手机', + } + }] def _real_extract(self, url): @@ -29,9 +49,14 @@ def _fetch_data(vid_id, mytv=False): else: base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' - return self._download_json( - base_data_url + vid_id, video_id, - 'Downloading JSON data for %s' % vid_id) + req = compat_urllib_request.Request(base_data_url + vid_id) + + cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') + if cn_verification_proxy: + req.add_header('Ytdl-request-proxy', cn_verification_proxy) + + return self._download_json(req, video_id, + 'Downloading JSON data for %s' % vid_id) mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') @@ -77,6 +102,11 @@ def _fetch_data(vid_id, mytv=False): % (format_id, i + 1, part_count)) part_info = part_str.split('|') + + # Sanitize URL to prevent download failure + if part_info[0][-1] == '/' and su[i][0] == '/': + su[i] = su[i][1:] + video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) formats.append({ From 5c7495a19429e3b27c003a4bd5bb96ed1e3a4932 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 6 Mar 2015 02:48:27 +0800 Subject: [PATCH 2/5] [sohu] Correct wrong imports --- youtube_dl/extractor/sohu.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index ef7ec51df..335e84fab 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -4,8 +4,10 @@ import re from .common import InfoExtractor -from ..utils import compat_str -from ..compat import compat_urllib_request +from ..compat import ( + compat_str, + compat_urllib_request +) class SohuIE(InfoExtractor): From 55969016e96fded28b97b2ef3bbf66efa83d6afb Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 6 Mar 2015 12:43:49 +0800 Subject: [PATCH 3/5] [utils] Add a function to sanitize consecutive slashes in URLs --- test/test_utils.py | 16 ++++++++++++++++ youtube_dl/extractor/sohu.py | 8 +++----- youtube_dl/utils.py | 15 +++++++++++++++ 3 files changed, 34 insertions(+), 5 deletions(-) diff --git a/test/test_utils.py b/test/test_utils.py index 64fad58ad..e02069c4d 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -54,6 +54,7 @@ xpath_with_ns, render_table, match_str, + url_sanitize_consecutive_slashes, ) @@ -501,6 +502,21 @@ def test_match_str(self): 'like_count > 100 & dislike_count Date: Sun, 15 Mar 2015 00:59:49 +0800 Subject: [PATCH 4/5] [Sohu] Add a multiplart video test case --- youtube_dl/extractor/sohu.py | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 5adc734d9..7db5b2f13 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -42,6 +42,37 @@ class SohuIE(InfoExtractor): 'ext': 'mp4', 'title': '【爱范品】第31期:MWC见不到的奇葩手机', } + }, { + 'note': 'Multipart video', + 'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml', + 'info_dict': { + 'id': '78910339', + }, + 'playlist': [{ + 'md5': 'bdbfb8f39924725e6589c146bc1883ad', + 'info_dict': { + 'id': '78910339_part1', + 'ext': 'mp4', + 'duration': 294, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }, { + 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e', + 'info_dict': { + 'id': '78910339_part2', + 'ext': 'mp4', + 'duration': 300, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }, { + 'md5': '8407e634175fdac706766481b9443450', + 'info_dict': { + 'id': '78910339_part3', + 'ext': 'mp4', + 'duration': 150, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }] }] def _real_extract(self, url): From 2cb434e53ee861c8bcbd538455be107085f444ae Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sun, 15 Mar 2015 01:05:01 +0800 Subject: [PATCH 5/5] [Sohu] Fix title extraction --- youtube_dl/extractor/sohu.py | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 7db5b2f13..ea5cc06b9 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -73,6 +73,17 @@ class SohuIE(InfoExtractor): 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', } }] + }, { + 'info': 'Video with title containing dash', + 'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml', + 'info_dict': { + 'id': '78932792', + 'ext': 'mp4', + 'title': 'youtube-dl testing video', + }, + 'params': { + 'skip_download': True + } }] def _real_extract(self, url): @@ -97,10 +108,8 @@ def _fetch_data(vid_id, mytv=False): mytv = mobj.group('mytv') is not None webpage = self._download_webpage(url, video_id) - raw_title = self._html_search_regex( - r'(?s)(.+?)', - webpage, 'video title') - title = raw_title.partition('-')[0].strip() + + title = self._og_search_title(webpage) vid = self._html_search_regex( r'var vid ?= ?["\'](\d+)["\']',