Revert "[sohu] Update extractor"

This reverts commit 32060c6d6b.
This commit is contained in:
Yen Chi Hsuan 2015-06-21 23:29:40 +08:00
parent 6f96e308d0
commit 3f3308cd75
1 changed files with 26 additions and 20 deletions

View File

@ -8,7 +8,10 @@ from ..compat import (
compat_str, compat_str,
compat_urllib_request compat_urllib_request
) )
from ..utils import ExtractorError from ..utils import (
sanitize_url_path_consecutive_slashes,
ExtractorError,
)
class SohuIE(InfoExtractor): class SohuIE(InfoExtractor):
@ -26,7 +29,7 @@ class SohuIE(InfoExtractor):
'skip': 'On available in China', 'skip': 'On available in China',
}, { }, {
'url': 'http://tv.sohu.com/20150305/n409385080.shtml', 'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a', 'md5': '699060e75cf58858dd47fb9c03c42cfb',
'info_dict': { 'info_dict': {
'id': '409385080', 'id': '409385080',
'ext': 'mp4', 'ext': 'mp4',
@ -34,7 +37,7 @@ class SohuIE(InfoExtractor):
} }
}, { }, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml', 'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
'md5': '49308ff6dafde5ece51137d04aec311e', 'md5': '9bf34be48f2f4dadcb226c74127e203c',
'info_dict': { 'info_dict': {
'id': '78693464', 'id': '78693464',
'ext': 'mp4', 'ext': 'mp4',
@ -48,7 +51,7 @@ class SohuIE(InfoExtractor):
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}, },
'playlist': [{ 'playlist': [{
'md5': '492923eac023ba2f13ff69617c32754a', 'md5': 'bdbfb8f39924725e6589c146bc1883ad',
'info_dict': { 'info_dict': {
'id': '78910339_part1', 'id': '78910339_part1',
'ext': 'mp4', 'ext': 'mp4',
@ -56,7 +59,7 @@ class SohuIE(InfoExtractor):
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
} }
}, { }, {
'md5': 'de604848c0e8e9c4a4dde7e1347c0637', 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
'info_dict': { 'info_dict': {
'id': '78910339_part2', 'id': '78910339_part2',
'ext': 'mp4', 'ext': 'mp4',
@ -64,7 +67,7 @@ class SohuIE(InfoExtractor):
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
} }
}, { }, {
'md5': '93584716ee0657c0b205b8aa3d27aa13', 'md5': '8407e634175fdac706766481b9443450',
'info_dict': { 'info_dict': {
'id': '78910339_part3', 'id': '78910339_part3',
'ext': 'mp4', 'ext': 'mp4',
@ -139,21 +142,24 @@ class SohuIE(InfoExtractor):
for i in range(part_count): for i in range(part_count):
formats = [] formats = []
for format_id, format_data in formats_json.items(): for format_id, format_data in formats_json.items():
data = format_data['data'] allot = format_data['allot']
prot = format_data['prot']
# URLs starts with http://newflv.sohu.ccgslb.net/ is not usable data = format_data['data']
# so retry until got a working URL clips_url = data['clipsURL']
video_url = 'newflv.sohu.ccgslb.net' su = data['su']
retries = 0
while 'newflv.sohu.ccgslb.net' in video_url and retries < 5: part_str = self._download_webpage(
download_note = 'Download information from CDN gateway for format ' + format_id 'http://%s/?prot=%s&file=%s&new=%s' %
if retries > 0: (allot, prot, clips_url[i], su[i]),
download_note += ' (retry #%d)' % retries video_id,
retries += 1 'Downloading %s video URL part %d of %d'
cdn_info = self._download_json( % (format_id, i + 1, part_count))
'http://data.vod.itc.cn/cdnList?new=' + data['su'][i],
video_id, download_note) part_info = part_str.split('|')
video_url = cdn_info['url']
video_url = sanitize_url_path_consecutive_slashes(
'%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
formats.append({ formats.append({
'url': video_url, 'url': video_url,