# coding: utf-8
from __future__ import unicode_literals
+import base64
import datetime
+import hashlib
import re
import time
-import base64
-import hashlib
from .common import InfoExtractor
from ..compat import (
- compat_urllib_parse,
compat_ord,
compat_str,
+ compat_urllib_parse,
)
from ..utils import (
determine_ext,
+ encode_data_uri,
ExtractorError,
+ int_or_none,
+ orderedSet,
parse_iso8601,
sanitized_Request,
- int_or_none,
str_or_none,
- encode_data_uri,
url_basename,
)
class LetvIE(InfoExtractor):
IE_DESC = '乐视网'
- _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
+ _VALID_URL = r'http://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
+
+ _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
_TESTS = [{
- 'url': 'http://www.letv.com/ptv/vplay/22005890.html',
+ 'url': 'http://www.le.com/ptv/vplay/22005890.html',
'md5': 'edadcfe5406976f42f9f266057ee5e40',
'info_dict': {
'id': '22005890',
'hls_prefer_native': True,
},
}, {
- 'url': 'http://www.letv.com/ptv/vplay/1415246.html',
+ 'url': 'http://www.le.com/ptv/vplay/1415246.html',
'info_dict': {
'id': '1415246',
'ext': 'mp4',
},
}, {
'note': 'This video is available only in Mainland China, thus a proxy is needed',
- 'url': 'http://www.letv.com/ptv/vplay/1118082.html',
+ 'url': 'http://www.le.com/ptv/vplay/1118082.html',
'md5': '2424c74948a62e5f31988438979c5ad1',
'info_dict': {
'id': '1118082',
'splatid': 101,
'format': 1,
'tkey': self.calc_time_key(int(time.time())),
- 'domain': 'www.letv.com'
+ 'domain': 'www.le.com'
}
play_json_req = sanitized_Request(
- 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
+ 'http://api.le.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
)
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
if cn_verification_proxy:
}
-class LetvTvIE(InfoExtractor):
- _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
+class LetvPlaylistIE(InfoExtractor):
+ _VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
+
_TESTS = [{
- 'url': 'http://www.letv.com/tv/46177.html',
+ 'url': 'http://www.le.com/tv/46177.html',
'info_dict': {
'id': '46177',
'title': '美人天下',
'description': 'md5:395666ff41b44080396e59570dbac01c'
},
'playlist_count': 35
- }]
-
- def _real_extract(self, url):
- playlist_id = self._match_id(url)
- page = self._download_webpage(url, playlist_id)
-
- media_urls = list(set(re.findall(
- r'http://www.letv.com/ptv/vplay/\d+.html', page)))
- entries = [self.url_result(media_url, ie='Letv')
- for media_url in media_urls]
-
- title = self._html_search_meta('keywords', page,
- fatal=False).split(',')[0]
- description = self._html_search_meta('description', page, fatal=False)
-
- return self.playlist_result(entries, playlist_id, playlist_title=title,
- playlist_description=description)
-
-
-class LetvPlaylistIE(LetvTvIE):
- _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
- _TESTS = [{
- 'url': 'http://tv.letv.com/izt/wuzetian/index.html',
+ }, {
+ 'url': 'http://tv.le.com/izt/wuzetian/index.html',
'info_dict': {
'id': 'wuzetian',
'title': '武媚娘传奇',
# This playlist contains some extra videos other than the drama itself
'playlist_mincount': 96
}, {
- 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
+ 'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml',
'info_dict': {
'id': 'lswjzzjc',
# The title should be "劲舞青春", but I can't find a simple way to
'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
},
'playlist_mincount': 7
+ }, {
+ 'url': 'http://www.le.com/comic/92063.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://list.le.com/listn/c1009_sc532002_d2_p1_o1.html',
+ 'only_matching': True,
}]
+ @classmethod
+ def suitable(cls, url):
+ return False if LetvIE.suitable(url) else super(LetvPlaylistIE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+ page = self._download_webpage(url, playlist_id)
+
+ # Currently old domain names are still used in playlists
+ media_ids = orderedSet(re.findall(
+ r'<a[^>]+href="http://www\.letv\.com/ptv/vplay/(\d+)\.html', page))
+ entries = [self.url_result(LetvIE._URL_TEMPLATE % media_id, ie='Letv')
+ for media_id in media_ids]
+
+ title = self._html_search_meta('keywords', page,
+ fatal=False).split(',')[0]
+ description = self._html_search_meta('description', page, fatal=False)
+
+ return self.playlist_result(entries, playlist_id, playlist_title=title,
+ playlist_description=description)
+
class LetvCloudIE(InfoExtractor):
IE_DESC = '乐视云'