aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2016-02-24 03:32:12 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2016-02-24 03:32:29 +0800
commit1b77ee6248b2a9967d3d3e809e416bd26fd7342c (patch)
treeeb42d815870b386dd5db6407bd6ec6032f07503c
parentbf4b3b6bd91137b94d5ae8ac6dc421e64a647355 (diff)
[c56] Support videos hosted on Sohu (closes #8073)
-rw-r--r--youtube_dl/extractor/c56.py22
1 files changed, 20 insertions, 2 deletions
diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py
index cb96c3876..cac8fdcba 100644
--- a/youtube_dl/extractor/c56.py
+++ b/youtube_dl/extractor/c56.py
@@ -4,12 +4,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..utils import js_to_json
class C56IE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
IE_NAME = '56.com'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
'md5': 'e59995ac63d0457783ea05f93f12a866',
'info_dict': {
@@ -18,12 +19,29 @@ class C56IE(InfoExtractor):
'title': '网事知多少 第32期:车怒',
'duration': 283.813,
},
- }
+ }, {
+ 'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
+ 'md5': '',
+ 'info_dict': {
+ 'id': '82247482',
+ 'title': '爱的诅咒之杜鹃花开',
+ },
+ 'playlist_count': 7,
+ 'add_ie': ['Sohu'],
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
text_id = mobj.group('textid')
+ webpage = self._download_webpage(url, text_id)
+ sohu_video_info_str = self._search_regex(
+ r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
+ if sohu_video_info_str:
+ sohu_video_info = self._parse_json(
+ sohu_video_info_str, text_id, transform_source=js_to_json)
+ return self.url_result(sohu_video_info['url'], 'Sohu')
+
page = self._download_json(
'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')