[letv] Correct regular expressions and fix a typo

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

diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py
index 9665ece89c9bc4cd64707ca3f7516749e4a33e91..ba8126f75e36d92c61086bbc7c57de1b11ed0b77 100644 (file)
--- a/youtube_dl/extractor/letv.py
+++ b/youtube_dl/extractor/letv.py
@@ -1,36 +1,39 @@
 # 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',
@@ -42,7 +45,7 @@ class LetvIE(InfoExtractor):
             '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',
@@ -54,7 +57,7 @@ class LetvIE(InfoExtractor):
         },
     }, {
         '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',
@@ -94,17 +97,16 @@ class LetvIE(InfoExtractor):
             return encrypted_data
         encrypted_data = encrypted_data[5:]
 
-        _loc4_ = bytearray()
-        while encrypted_data:
-            b = compat_ord(encrypted_data[0])
-            _loc4_.extend([b // 16, b & 0x0f])
-            encrypted_data = encrypted_data[1:]
+        _loc4_ = bytearray(2 * len(encrypted_data))
+        for idx, val in enumerate(encrypted_data):
+            b = compat_ord(val)
+            _loc4_[2 * idx] = b // 16
+            _loc4_[2 * idx + 1] = b % 16
         idx = len(_loc4_) - 11
         _loc4_ = _loc4_[idx:] + _loc4_[:idx]
-        _loc7_ = bytearray()
-        while _loc4_:
-            _loc7_.append(_loc4_[0] * 16 + _loc4_[1])
-            _loc4_ = _loc4_[2:]
+        _loc7_ = bytearray(len(encrypted_data))
+        for i in range(len(encrypted_data)):
+            _loc7_[i] = _loc4_[2 * i] * 16 + _loc4_[2 * i + 1]
 
         return bytes(_loc7_)
 
@@ -117,10 +119,10 @@ class LetvIE(InfoExtractor):
             '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:
@@ -194,9 +196,9 @@ class LetvIE(InfoExtractor):
 
 
 class LetvTvIE(InfoExtractor):
-    _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
+    _VALID_URL = r'http://www\.le\.com/tv/(?P<id>\d+)\.html'
     _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',
@@ -209,10 +211,11 @@ class LetvTvIE(InfoExtractor):
         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]
+        # Currently old domain names are still used in playlists
+        media_ids = orderedSet(re.findall(
+            r'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]
@@ -223,9 +226,9 @@ class LetvTvIE(InfoExtractor):
 
 
 class LetvPlaylistIE(LetvTvIE):
-    _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
+    _VALID_URL = r'http://tv\.le\.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',
@@ -234,7 +237,7 @@ class LetvPlaylistIE(LetvTvIE):
         # 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