Register new version in the changelog.

[youtubedl] / youtube_dl / extractor / imdb.py

diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index f40769eac0361594ac64f6ad4ccba7d35281333a..02e1e428e9e41ba75a2ff5c37c7cf0732682c111 100644 (file)
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -5,8 +5,7 @@ import json
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    compat_urlparse,
-    get_element_by_attribute,
+    qualities,

 )
 
 
 )
 
 


@@ -17,7 +16,6 @@ class ImdbIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
 
     _TEST = {
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',

-        'md5': '9f34fa777ade3a6e57a054fdbcb3a068',

         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',
         'info_dict': {
             'id': '2524815897',
             'ext': 'mp4',


@@ -27,28 +25,38 @@ class ImdbIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)

-        descr = get_element_by_attribute('itemprop', 'description', webpage)
-        available_formats = re.findall(
-            r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
-            flags=re.MULTILINE)
+        descr = self._html_search_regex(
+            r'(?s)<span itemprop="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
+        player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
+        player_page = self._download_webpage(
+            player_url, video_id, 'Downloading player page')
+        # the player page contains the info for the default format, we have to
+        # fetch other pages for the rest of the formats
+        extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
+        format_pages = [
+            self._download_webpage(
+                f_url, video_id, 'Downloading info for %s format' % f_name)
+            for f_url, f_name in extra_formats]
+        format_pages.append(player_page)
+
+        quality = qualities(['SD', '480p', '720p'])

         formats = []
         formats = []

-        for f_id, f_path in available_formats:
-            f_path = f_path.strip()
-            format_page = self._download_webpage(
-                compat_urlparse.urljoin(url, f_path),
-                'Downloading info for %s format' % f_id)
+        for format_page in format_pages:

             json_data = self._search_regex(
                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
                 format_page, 'json data', flags=re.DOTALL)
             info = json.loads(json_data)
             format_info = info['videoPlayerObject']['video']
             json_data = self._search_regex(
                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
                 format_page, 'json data', flags=re.DOTALL)
             info = json.loads(json_data)
             format_info = info['videoPlayerObject']['video']

+            f_id = format_info['ffname']

             formats.append({
                 'format_id': f_id,
             formats.append({
                 'format_id': f_id,

-                'url': format_info['url'],
+                'url': format_info['videoInfoList'][0]['videoUrl'],
+                'quality': quality(f_id),

             })
             })

+        self._sort_formats(formats)

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,


@@ -63,27 +71,23 @@ class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
     _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
     _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'

-    
+    _TEST = {
+        'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
+        'info_dict': {
+            'id': 'JFs9NWw6XI0',
+            'title': 'March 23, 2012 Releases',
+        },
+        'playlist_count': 7,
+    }
+

     def _real_extract(self, url):
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        list_id = mobj.group('id')
-        
-        # RSS XML is sometimes malformed
-        rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, 'Downloading list RSS')
-        list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, 'list title')
-        
-        # Export is independent of actual author_id, but returns 404 if no author_id is provided.
-        # However, passing dummy author_id seems to be enough.
-        csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
-                                     list_id, 'Downloading list CSV')
-        
-        entries = []
-        for item in csv.split('\n')[1:]:
-            cols = item.split(',')
-            if len(cols) < 2:
-                continue
-            item_id = cols[1][1:-1]
-            if item_id.startswith('vi'):
-                entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
-        
+        list_id = self._match_id(url)
+        webpage = self._download_webpage(url, list_id)
+        entries = [
+            self.url_result('http://www.imdb.com' + m, 'Imdb')
+            for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
+
+        list_title = self._html_search_regex(
+            r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
+

         return self.playlist_result(entries, list_id, list_title)
         return self.playlist_result(entries, list_id, list_title)