Merge branch 'shahid' of https://github.com/remitamine/youtube-dl into remitamine...

[youtube-dl] / youtube_dl / extractor / iqiyi.py

diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py
index 840cc9a4d8cc69bf083492004b9858848a9bf390..393e67e354c4adb9864bdebfe05c38503be67b0b 100644 (file)
--- a/youtube_dl/extractor/iqiyi.py
+++ b/youtube_dl/extractor/iqiyi.py
@@ -4,10 +4,8 @@ from __future__ import unicode_literals
 import hashlib
 import math
 import random
-import re
 import time
 import uuid
-import zlib
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse
@@ -16,10 +14,11 @@ from ..utils import ExtractorError
 
 class IqiyiIE(InfoExtractor):
     IE_NAME = 'iqiyi'
+    IE_DESC = '爱奇艺'
 
-    _VALID_URL = r'http://(?:www\.)iqiyi.com/.+?\.html'
+    _VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
         'md5': '2cb594dc2781e6c941a110d8f358118b',
         'info_dict': {
@@ -27,7 +26,74 @@ class IqiyiIE(InfoExtractor):
             'title': '美国德州空中惊现奇异云团 酷似UFO',
             'ext': 'f4v',
         }
-    }
+    }, {
+        'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
+        'info_dict': {
+            'id': 'e3f585b550a280af23c98b6cb2be19fb',
+            'title': '名侦探柯南第752集',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part1',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part2',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part3',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part4',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part5',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part6',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part7',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part8',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }],
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _FORMATS_MAP = [
+        ('1', 'h6'),
+        ('2', 'h5'),
+        ('3', 'h4'),
+        ('4', 'h3'),
+        ('5', 'h2'),
+        ('10', 'h1'),
+    ]
 
     def construct_video_urls(self, data, video_id, _uuid):
         def do_xor(x, y):
@@ -104,27 +170,12 @@ class IqiyiIE(InfoExtractor):
         return video_urls_dict
 
     def get_format(self, bid):
-        _dict = {
-            '1': 'h6',
-            '2': 'h5',
-            '3': 'h4',
-            '4': 'h3',
-            '5': 'h2',
-            '10': 'h1'
-        }
-        return _dict.get(str(bid), None)
+        matched_format_ids = [_format_id for _bid, _format_id in self._FORMATS_MAP if _bid == str(bid)]
+        return matched_format_ids[0] if len(matched_format_ids) else None
 
     def get_bid(self, format_id):
-        _dict = {
-            'h6': '1',
-            'h5': '2',
-            'h4': '3',
-            'h3': '4',
-            'h2': '5',
-            'h1': '10',
-            'best': 'best'
-        }
-        return _dict.get(format_id, None)
+        matched_bids = [_bid for _bid, _format_id in self._FORMATS_MAP if _format_id == format_id]
+        return matched_bids[0] if len(matched_bids) else None
 
     def get_raw_data(self, tvid, video_id, enc_key, _uuid):
         tm = str(int(time.time()))
@@ -150,12 +201,7 @@ class IqiyiIE(InfoExtractor):
         return raw_data
 
     def get_enc_key(self, swf_url, video_id):
-        req = self._request_webpage(
-            swf_url, video_id, note='download swf content')
-        cn = req.read()
-        cn = zlib.decompress(cn[8:])
-        pt = re.compile(b'MixerRemote\x08(?P<enc_key>.+?)\$&vv')
-        enc_key = self._search_regex(pt, cn, 'enc_key').decode('utf8')
+        enc_key = '3601ba290e4f4662848c710e2122007e'  # last update at 2015-08-10 for Zombie
         return enc_key
 
     def _real_extract(self, url):
@@ -166,7 +212,7 @@ class IqiyiIE(InfoExtractor):
         video_id = self._search_regex(
             r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
         swf_url = self._search_regex(
-            r'(http://.+?MainPlayer.+?\.swf)', webpage, 'swf player URL')
+            r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
         _uuid = uuid.uuid4().hex
 
         enc_key = self.get_enc_key(swf_url, video_id)