Merge tag 'upstream/2017.02.24.1'

[youtubedl] / youtube_dl / extractor / drtuber.py

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index 639f9182c5484a22f0056e25fc6aa7e56f193df5..1eca82b3b46ae47e511b0f2f3f8bd6bb505cdc23 100644 (file)
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -3,12 +3,15 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import str_to_int
+from ..utils import (
+    NO_DEFAULT,
+    str_to_int,
+)

 
 
 class DrTuberIE(InfoExtractor):
 
 
 class DrTuberIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
+    _TESTS = [{

         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {


@@ -17,44 +20,57 @@ class DrTuberIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'hot perky blonde naked golf',
             'like_count': int,
             'ext': 'mp4',
             'title': 'hot perky blonde naked golf',
             'like_count': int,

-            'dislike_count': int,

             'comment_count': int,
             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
             'comment_count': int,
             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],

-            'thumbnail': 're:https?://.*\.jpg$',
+            'thumbnail': r're:https?://.*\.jpg$',

             'age_limit': 18,
         }
             'age_limit': 18,
         }

-    }
+    }, {
+        'url': 'http://www.drtuber.com/embed/489939',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
+            webpage)

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id

 
 

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

 
         video_url = self._html_search_regex(
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
 
         video_url = self._html_search_regex(
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(

-            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
+            (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
+             r'<p[^>]+class="title_substrate">([^<]+)</p>',
+             r'<title>([^<]+) - \d+'),

             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 

-        def extract_count(id_, name):
+        def extract_count(id_, name, default=NO_DEFAULT):

             return str_to_int(self._html_search_regex(
                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
             return str_to_int(self._html_search_regex(
                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,

-                webpage, '%s count' % name, fatal=False))
+                webpage, '%s count' % name, default=default, fatal=False))

 
         like_count = extract_count('rate_likes', 'like')
 
         like_count = extract_count('rate_likes', 'like')

-        dislike_count = extract_count('rate_dislikes', 'dislike')
+        dislike_count = extract_count('rate_dislikes', 'dislike', default=None)

         comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(
         comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(

-            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
-        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
+            r'<div[^>]+class="categories_list">(.+?)</div>',
+            webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(
+            r'<a title="([^"]+)"', cats_str)

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