aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2015-05-09 13:54:28 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2015-05-09 14:02:11 +0800
commit32060c6d6b618fa858b2ce43db34d02fd43bc542 (patch)
tree6bd20c712a0cc548850cdec4242c241812f627ea /youtube_dl/extractor
parent3dbec410a0e195036025aa3a3792932783f371d2 (diff)
[sohu] Update extractor
The original extraction logic always fails for all test videos
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/sohu.py44
1 files changed, 19 insertions, 25 deletions
diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index 13b9e9133..eab4adfca 100644
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -8,10 +8,7 @@ from ..compat import (
compat_str,
compat_urllib_request
)
-from ..utils import (
- sanitize_url_path_consecutive_slashes,
- ExtractorError,
-)
+from ..utils import ExtractorError
class SohuIE(InfoExtractor):
@@ -31,7 +28,7 @@ class SohuIE(InfoExtractor):
}
}, {
'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
- 'md5': '699060e75cf58858dd47fb9c03c42cfb',
+ 'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a',
'info_dict': {
'id': '409385080',
'ext': 'mp4',
@@ -39,7 +36,7 @@ class SohuIE(InfoExtractor):
}
}, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
- 'md5': '9bf34be48f2f4dadcb226c74127e203c',
+ 'md5': '49308ff6dafde5ece51137d04aec311e',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
@@ -53,7 +50,7 @@ class SohuIE(InfoExtractor):
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
},
'playlist': [{
- 'md5': 'bdbfb8f39924725e6589c146bc1883ad',
+ 'md5': '492923eac023ba2f13ff69617c32754a',
'info_dict': {
'id': '78910339_part1',
'ext': 'mp4',
@@ -61,7 +58,7 @@ class SohuIE(InfoExtractor):
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
- 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
+ 'md5': 'de604848c0e8e9c4a4dde7e1347c0637',
'info_dict': {
'id': '78910339_part2',
'ext': 'mp4',
@@ -69,7 +66,7 @@ class SohuIE(InfoExtractor):
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
- 'md5': '8407e634175fdac706766481b9443450',
+ 'md5': '93584716ee0657c0b205b8aa3d27aa13',
'info_dict': {
'id': '78910339_part3',
'ext': 'mp4',
@@ -144,24 +141,21 @@ class SohuIE(InfoExtractor):
for i in range(part_count):
formats = []
for format_id, format_data in formats_json.items():
- allot = format_data['allot']
- prot = format_data['prot']
-
data = format_data['data']
- clips_url = data['clipsURL']
- su = data['su']
-
- part_str = self._download_webpage(
- 'http://%s/?prot=%s&file=%s&new=%s' %
- (allot, prot, clips_url[i], su[i]),
- video_id,
- 'Downloading %s video URL part %d of %d'
- % (format_id, i + 1, part_count))
-
- part_info = part_str.split('|')
- video_url = sanitize_url_path_consecutive_slashes(
- '%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
+ # URLs starts with http://newflv.sohu.ccgslb.net/ is not usable
+ # so retry until got a working URL
+ video_url = 'newflv.sohu.ccgslb.net'
+ retries = 0
+ while 'newflv.sohu.ccgslb.net' in video_url and retries < 5:
+ download_note = 'Download information from CDN gateway for format ' + format_id
+ if retries > 0:
+ download_note += ' (retry #%d)' % retries
+ retries += 1
+ cdn_info = self._download_json(
+ 'http://data.vod.itc.cn/cdnList?new=' + data['su'][i],
+ video_id, download_note)
+ video_url = cdn_info['url']
formats.append({
'url': video_url,