aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py4
-rw-r--r--youtube_dl/extractor/letv.py80
-rw-r--r--youtube_dl/extractor/weiqitv.py52
3 files changed, 135 insertions, 1 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 0cc339a37..bab3d7b46 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -337,7 +337,8 @@ from .lemonde import LemondeIE
from .letv import (
LetvIE,
LetvTvIE,
- LetvPlaylistIE
+ LetvPlaylistIE,
+ LetvCloudIE,
)
from .libsyn import LibsynIE
from .lifenews import (
@@ -857,6 +858,7 @@ from .webofstories import (
WebOfStoriesPlaylistIE,
)
from .weibo import WeiboIE
+from .weiqitv import WeiqiTVIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py
index be648000e..08bdae8a2 100644
--- a/youtube_dl/extractor/letv.py
+++ b/youtube_dl/extractor/letv.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
import datetime
import re
import time
+import base64
from .common import InfoExtractor
from ..compat import (
@@ -16,7 +17,9 @@ from ..utils import (
parse_iso8601,
sanitized_Request,
int_or_none,
+ str_or_none,
encode_data_uri,
+ url_basename,
)
@@ -239,3 +242,80 @@ class LetvPlaylistIE(LetvTvIE):
},
'playlist_mincount': 7
}]
+
+
+class LetvCloudIE(InfoExtractor):
+ IE_DESC = '乐视云'
+ _VALID_URL = r'https?://yuntv\.letv\.com/bcloud.html\?.+'
+
+ _TESTS = [{
+ 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=467623dedf',
+ 'md5': '26450599afd64c513bc77030ad15db44',
+ 'info_dict': {
+ 'id': 'p7jnfw5hw9_467623dedf',
+ 'ext': 'mp4',
+ 'title': 'Video p7jnfw5hw9_467623dedf',
+ },
+ }, {
+ 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
+ 'info_dict': {
+ 'id': 'p7jnfw5hw9_ec93197892',
+ 'ext': 'mp4',
+ 'title': 'Video p7jnfw5hw9_ec93197892',
+ },
+ }, {
+ 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
+ 'info_dict': {
+ 'id': 'p7jnfw5hw9_187060b6fd',
+ 'ext': 'mp4',
+ 'title': 'Video p7jnfw5hw9_187060b6fd',
+ },
+ }]
+
+ def _real_extract(self, url):
+ uu_mobj = re.search('uu=([\w]+)', url)
+ vu_mobj = re.search('vu=([\w]+)', url)
+
+ if not uu_mobj or not vu_mobj:
+ raise ExtractorError('Invalid URL: %s' % url, expected=True)
+
+ uu = uu_mobj.group(1)
+ vu = vu_mobj.group(1)
+ media_id = uu + '_' + vu
+
+ play_json_req = sanitized_Request(
+ 'http://api.letvcloud.com/gpc.php?cf=html5&sign=signxxxxx&ver=2.2&format=json&' +
+ 'uu=' + uu + '&vu=' + vu)
+ play_json = self._download_json(play_json_req, media_id, 'Downloading playJson data')
+
+ if not play_json.get('data'):
+ if play_json.get('message'):
+ raise ExtractorError('Letv cloud said: %s' % play_json['message'], expected=True)
+ elif play_json.get('code'):
+ raise ExtractorError('Letv cloud returned error %d' % play_json['code'], expected=True)
+ else:
+ raise ExtractorError('Letv cloud returned an unknwon error')
+
+ def b64decode(s):
+ return base64.b64decode(s.encode('utf-8')).decode('utf-8')
+
+ formats = []
+ for media in play_json['data']['video_info']['media'].values():
+ play_url = media['play_url']
+ url = b64decode(play_url['main_url'])
+ decoded_url = b64decode(url_basename(url))
+ formats.append({
+ 'url': url,
+ 'ext': determine_ext(decoded_url),
+ 'format_id': int_or_none(play_url.get('vtype')),
+ 'format_note': str_or_none(play_url.get('definition')),
+ 'width': int_or_none(play_url.get('vwidth')),
+ 'height': int_or_none(play_url.get('vheight')),
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': media_id,
+ 'title': 'Video %s' % media_id,
+ 'formats': formats,
+ }
diff --git a/youtube_dl/extractor/weiqitv.py b/youtube_dl/extractor/weiqitv.py
new file mode 100644
index 000000000..e333ae345
--- /dev/null
+++ b/youtube_dl/extractor/weiqitv.py
@@ -0,0 +1,52 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class WeiqiTVIE(InfoExtractor):
+ IE_DESC = 'WQTV'
+ _VALID_URL = r'http://www\.weiqitv\.com/index/video_play\?videoId=(?P<id>[A-Za-z0-9]+)'
+
+ _TESTS = [{
+ 'url': 'http://www.weiqitv.com/index/video_play?videoId=53c744f09874f0e76a8b46f3',
+ 'md5': '26450599afd64c513bc77030ad15db44',
+ 'info_dict': {
+ 'id': '53c744f09874f0e76a8b46f3',
+ 'ext': 'mp4',
+ 'title': '2013年度盘点',
+ },
+ }, {
+ 'url': 'http://www.weiqitv.com/index/video_play?videoId=567379a2d4c36cca518b4569',
+ 'info_dict': {
+ 'id': '567379a2d4c36cca518b4569',
+ 'ext': 'mp4',
+ 'title': '民国围棋史',
+ },
+ }, {
+ 'url': 'http://www.weiqitv.com/index/video_play?videoId=5430220a9874f088658b4567',
+ 'info_dict': {
+ 'id': '5430220a9874f088658b4567',
+ 'ext': 'mp4',
+ 'title': '二路托过的手段和运用',
+ },
+ }]
+
+ def _real_extract(self, url):
+ media_id = self._match_id(url)
+ page = self._download_webpage(url, media_id)
+
+ info_json_str = self._search_regex(
+ 'var\s+video\s*=\s*(.+});', page, 'info json str')
+ info_json = self._parse_json(info_json_str, media_id)
+
+ letvcloud_url = self._search_regex(
+ 'var\s+letvurl\s*=\s*"([^"]+)', page, 'letvcloud url')
+
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': 'LetvCloud',
+ 'url': letvcloud_url,
+ 'title': info_json['name'],
+ 'id': media_id,
+ }