Merge pull request #9400 from inondle/master

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

diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py
index 712368fafd0cf66f09146dfbed36a91d4651b11d..f7339702cad3ed2804fe276b9d1fc6857c368206 100644 (file)
--- a/youtube_dl/extractor/einthusan.py
+++ b/youtube_dl/extractor/einthusan.py
@@ -1,22 +1,26 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    remove_start,
+    sanitized_Request,
+)
 
 
 class EinthusanIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?einthusan\.com/movies/watch.php\?(.*)?id=(?P<id>[0-9]+).*?'
+    _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
     _TESTS = [
         {
-            'url': 'http://www.einthusan.com/movies/watch.php?hindimoviesonline=Ek+Villain&lang=hindi&id=2447',
+            'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
             'md5': 'af244f4458cd667205e513d75da5b8b1',
             'info_dict': {
                 'id': '2447',
                 'ext': 'mp4',
                 'title': 'Ek Villain',
                 'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
             }
         },
         {
@@ -27,28 +31,40 @@ class EinthusanIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Soodhu Kavvuum',
                 'thumbnail': 're:^https?://.*\.jpg$',
+                'description': 'md5:05d8a0c0281a4240d86d76e14f2f4d51',
             }
         },
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
+        video_id = self._match_id(url)
+
+        request = sanitized_Request(url)
+        request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
+        webpage = self._download_webpage(request, video_id)
+
+        title = self._html_search_regex(
+            r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>',
+            webpage, 'title')
 
-        video_title = self._html_search_regex(r'''<h1><a class="movie-title".*?>(.*?)</a></h1>''', webpage, 'title')
+        video_id = self._search_regex(
+            r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id)
 
-        video_url = self._html_search_regex(
-            r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video url')
+        video_url = self._download_webpage(
+            'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/'
+            % video_id, video_id)
 
-        thumb_rel_url = self._html_search_regex(
-            r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', webpage, "thumbnail url")
-        thumb_abs_url = re.sub('\.\.', 'http://www.einthusan.com', thumb_rel_url)
+        description = self._html_search_meta('description', webpage)
+        thumbnail = self._html_search_regex(
+            r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
+            webpage, "thumbnail url", fatal=False)
+        if thumbnail is not None:
+            thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..'))
 
         return {
             'id': video_id,
-            'ext': 'mp4',
-            'title': video_title,
+            'title': title,
             'url': video_url,
-            'thumbnail': thumb_abs_url,
+            'thumbnail': thumbnail,
+            'description': description,
         }