X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fletv.py;h=9ed81a1992acc8e527844e0242e6392abe37884f;hb=63fc80005782430180ed0d13ac6ab5ca497d333a;hp=d7d3156346afdb4c4314ba4cac5e33e9186fead6;hpb=570311610e33eb67d5a65a86705d54daaee17361;p=youtube-dl

diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py
index d7d315634..9ed81a199 100644
--- a/youtube_dl/extractor/letv.py
+++ b/youtube_dl/extractor/letv.py
@@ -1,14 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import os.path
+import datetime
 import re
 import time
-import datetime
 
 from .common import InfoExtractor
-from ..compat import (compat_urlparse, compat_urllib_parse)
-from ..utils import (ExtractorError, parse_iso8601)
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    parse_iso8601,
+)
 
 
 class LetvIE(InfoExtractor):
@@ -23,20 +30,36 @@ class LetvIE(InfoExtractor):
             'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
             'timestamp': 1424747397,
             'upload_date': '20150224',
+            'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
         }
     }, {
+        'url': 'http://www.letv.com/ptv/vplay/1415246.html',
+        'info_dict': {
+            'id': '1415246',
+            'ext': 'mp4',
+            'title': '美人天下01',
+            'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
+        },
+    }, {
+        'note': 'This video is available only in Mainland China, thus a proxy is needed',
         'url': 'http://www.letv.com/ptv/vplay/1118082.html',
+        'md5': 'f80936fbe20fb2f58648e81386ff7927',
         'info_dict': {
             'id': '1118082',
             'ext': 'mp4',
-        }
+            'title': '与龙共舞 完整版',
+            'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
+        },
+        'params': {
+            'cn_verification_proxy': 'http://proxy.uku.im:8888'
+        },
     }]
 
     @staticmethod
     def urshift(val, n):
         return val >> n if val >= 0 else (val + 0x100000000) >> n
 
-    # ror() and calcTimeKey() are reversed from a embedded swf file in KLetvPlayer.swf
+    # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
     def ror(self, param1, param2):
         _loc3_ = 0
         while _loc3_ < param2:
@@ -44,7 +67,7 @@ class LetvIE(InfoExtractor):
             _loc3_ += 1
         return param1
 
-    def calcTimeKey(self, param1):
+    def calc_time_key(self, param1):
         _loc2_ = 773625421
         _loc3_ = self.ror(param1, _loc2_ % 13)
         _loc3_ = _loc3_ ^ _loc2_
@@ -59,11 +82,18 @@ class LetvIE(InfoExtractor):
             'platid': 1,
             'splatid': 101,
             'format': 1,
-            'tkey': self.calcTimeKey(int(time.time())),
+            'tkey': self.calc_time_key(int(time.time())),
             'domain': 'www.letv.com'
         }
+        play_json_req = compat_urllib_request.Request(
+            'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
+        )
+        cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+        if cn_verification_proxy:
+            play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
+
         play_json = self._download_json(
-            'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params),
+            play_json_req,
             media_id, 'playJson data')
 
         # Check for errors
@@ -100,7 +130,8 @@ class LetvIE(InfoExtractor):
 
                 url_info_dict = {
                     'url': media_url,
-                    'ext': os.path.splitext(dispatch[format_id][1])[1][1:]
+                    'ext': determine_ext(dispatch[format_id][1]),
+                    'format_id': format_id,
                 }
 
                 if format_id[-1:] == 'p':
@@ -109,14 +140,16 @@ class LetvIE(InfoExtractor):
                 urls.append(url_info_dict)
 
         publish_time = parse_iso8601(self._html_search_regex(
-            r'发布时间&nbsp;([^<>]+) ', page, 'publish time', fatal=False),
+            r'发布时间&nbsp;([^<>]+) ', page, 'publish time', default=None),
             delimiter=' ', timezone=datetime.timedelta(hours=8))
+        description = self._html_search_meta('description', page, fatal=False)
 
         return {
             'id': media_id,
             'formats': urls,
             'title': playurl['title'],
             'thumbnail': playurl['pic'],
+            'description': description,
             'timestamp': publish_time,
         }
 
@@ -142,7 +175,8 @@ class LetvTvIE(InfoExtractor):
         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]
+        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,
@@ -158,13 +192,14 @@ class LetvPlaylistIE(LetvTvIE):
             'title': '武媚娘传奇',
             'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
         },
-        'playlist_count': 96
+        # This playlist contains some extra videos other than the drama itself
+        'playlist_mincount': 96
     }, {
         'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
         'info_dict': {
             'id': 'lswjzzjc',
-            # should be "劲舞青春", but I can't find a simple way to determine
-            # the playlist title
+            # The title should be "劲舞青春", but I can't find a simple way to
+            # determine the playlist title
             'title': '乐视午间自制剧场',
             'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
         },