New upstream version 2017.10.15.1

[youtubedl] / youtube_dl / extractor / redtube.py

diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py
index 721fc3a9e2d2b3431051ea00982f72ae1d98ff65..f70a75256c638f4a3ce9cda3b9577176e49f3cca 100644 (file)
--- a/youtube_dl/extractor/redtube.py
+++ b/youtube_dl/extractor/redtube.py
@@ -1,6 +1,9 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
     ExtractorError,
     int_or_none,
 from ..utils import (
     ExtractorError,
     int_or_none,


@@ -10,8 +13,8 @@ from ..utils import (
 
 
 class RedTubeIE(InfoExtractor):
 
 
 class RedTubeIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
+    _TESTS = [{

         'url': 'http://www.redtube.com/66418',
         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
         'info_dict': {
         'url': 'http://www.redtube.com/66418',
         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
         'info_dict': {


@@ -23,11 +26,21 @@ class RedTubeIE(InfoExtractor):
             'view_count': int,
             'age_limit': 18,
         }
             'view_count': int,
             'age_limit': 18,
         }

-    }
+    }, {
+        'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
+            webpage)

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://www.redtube.com/%s' % video_id, video_id)

 
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
 
         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
             raise ExtractorError('Video %s has been removed' % video_id, expected=True)


@@ -50,7 +63,23 @@ class RedTubeIE(InfoExtractor):
                         'format_id': format_id,
                         'height': int_or_none(format_id),
                     })
                         'format_id': format_id,
                         'height': int_or_none(format_id),
                     })

-        else:
+        medias = self._parse_json(
+            self._search_regex(
+                r'mediaDefinition\s*:\s*(\[.+?\])', webpage,
+                'media definitions', default='{}'),
+            video_id, fatal=False)
+        if medias and isinstance(medias, list):
+            for media in medias:
+                format_url = media.get('videoUrl')
+                if not format_url or not isinstance(format_url, compat_str):
+                    continue
+                format_id = media.get('quality')
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'height': int_or_none(format_id),
+                })
+        if not formats:

             video_url = self._html_search_regex(
                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
             formats.append({'url': video_url})
             video_url = self._html_search_regex(
                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
             formats.append({'url': video_url})


@@ -61,7 +90,7 @@ class RedTubeIE(InfoExtractor):
             r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
             webpage, 'upload date', fatal=False))
         duration = int_or_none(self._search_regex(
             r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
             webpage, 'upload date', fatal=False))
         duration = int_or_none(self._search_regex(

-            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))

         view_count = str_to_int(self._search_regex(
             r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
             webpage, 'view count', fatal=False))
         view_count = str_to_int(self._search_regex(
             r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
             webpage, 'view count', fatal=False))