]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/imdb.py
debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.
[youtubedl] / youtube_dl / extractor / imdb.py
index d8e9712a7acd39db97c8a55b2551137ca0e56a41..f2c1c10f5c1dec44129ea4cd7d4cff69c7c07206 100644 (file)
@@ -1,52 +1,53 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    get_element_by_attribute,
 )
 
 
 class ImdbIE(InfoExtractor):
-    IE_NAME = u'imdb'
-    IE_DESC = u'Internet Movie Database trailers'
-    _VALID_URL = r'http://www\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+    IE_NAME = 'imdb'
+    IE_DESC = 'Internet Movie Database trailers'
+    _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.imdb.com/video/imdb/vi2524815897',
-        u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068',
-        u'info_dict': {
-            u'id': u'2524815897',
-            u'ext': u'mp4',
-            u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
-            u'description': u'md5:9061c2219254e5d14e03c25c98e96a81',
-            u'duration': 151,
+        'url': 'http://www.imdb.com/video/imdb/vi2524815897',
+        'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
+        'info_dict': {
+            'id': '2524815897',
+            'ext': 'mp4',
+            'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
+            'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url,video_id)
-        descr = get_element_by_attribute('itemprop', 'description', webpage)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
+        descr = self._html_search_regex(
+            r'(?s)<span itemprop="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
         available_formats = re.findall(
             r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
             flags=re.MULTILINE)
         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),
-                u'Downloading info for %s format' % f_id)
+                'Downloading info for %s format' % f_id)
             json_data = self._search_regex(
                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
-                format_page, u'json data', flags=re.DOTALL)
+                format_page, 'json data', flags=re.DOTALL)
             info = json.loads(json_data)
             format_info = info['videoPlayerObject']['video']
             formats.append({
                 'format_id': f_id,
                 'url': format_info['url'],
-                'height': int(info['titleObject']['encoding']['selected'][:-1]),
             })
 
         return {
@@ -55,5 +56,30 @@ class ImdbIE(InfoExtractor):
             'formats': formats,
             'description': descr,
             'thumbnail': format_info['slate'],
-            'duration': int(info['titleObject']['title']['duration_seconds']),
         }
+
+
+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})'
+    _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):
+        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)