debian/copyright: use spaces rather than tabs to start continuation lines.

[youtubedl] / youtube_dl / extractor / drtuber.py

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index 1eca82b3b46ae47e511b0f2f3f8bd6bb505cdc23..2baea585bf6b8882d5816052ca734b1f9dbc024c 100644 (file)
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -4,13 +4,15 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    int_or_none,

     NO_DEFAULT,
     NO_DEFAULT,

+    parse_duration,

     str_to_int,
 )
 
 
 class DrTuberIE(InfoExtractor):
     str_to_int,
 )
 
 
 class DrTuberIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?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',
     _TESTS = [{
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',


@@ -28,6 +30,9 @@ class DrTuberIE(InfoExtractor):
     }, {
         'url': 'http://www.drtuber.com/embed/489939',
         'only_matching': True,
     }, {
         'url': 'http://www.drtuber.com/embed/489939',
         'only_matching': True,

+    }, {
+        'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
+        'only_matching': True,

     }]
 
     @staticmethod
     }]
 
     @staticmethod


@@ -44,11 +49,31 @@ class DrTuberIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://www.drtuber.com/video/%s' % video_id, 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')
+        video_data = self._download_json(
+            'http://www.drtuber.com/player_config_json/', video_id, query={
+                'vid': video_id,
+                'embed': 0,
+                'aid': 0,
+                'domain_id': 0,
+            })
+
+        formats = []
+        for format_id, video_url in video_data['files'].items():
+            if video_url:
+                formats.append({
+                    'format_id': format_id,
+                    'quality': 2 if format_id == 'hq' else 1,
+                    'url': video_url
+                })
+        self._sort_formats(formats)
+
+        duration = int_or_none(video_data.get('duration')) or parse_duration(
+            video_data.get('duration_format'))

 
         title = self._html_search_regex(
 
         title = self._html_search_regex(

-            (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
+            (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
+             r'<title>([^<]+)\s*@\s+DrTuber',
+             r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',

              r'<p[^>]+class="title_substrate">([^<]+)</p>',
              r'<title>([^<]+) - \d+'),
             webpage, 'title')
              r'<p[^>]+class="title_substrate">([^<]+)</p>',
              r'<title>([^<]+) - \d+'),
             webpage, 'title')


@@ -75,7 +100,7 @@ class DrTuberIE(InfoExtractor):
         return {
             'id': video_id,
             'display_id': display_id,
         return {
             'id': video_id,
             'display_id': display_id,

-            'url': video_url,
+            'formats': formats,

             'title': title,
             'thumbnail': thumbnail,
             'like_count': like_count,
             'title': title,
             'thumbnail': thumbnail,
             'like_count': like_count,


@@ -83,4 +108,5 @@ class DrTuberIE(InfoExtractor):
             'comment_count': comment_count,
             'categories': categories,
             'age_limit': self._rta_search(webpage),
             'comment_count': comment_count,
             'categories': categories,
             'age_limit': self._rta_search(webpage),

+            'duration': duration,

         }
         }