Update upstream source from tag 'upstream/2019.09.28'

[youtubedl] / youtube_dl / extractor / drtuber.py

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index ca274dff691f2ad34d027f31bf814c8df850812d..2baea585bf6b8882d5816052ca734b1f9dbc024c 100644 (file)
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -3,63 +3,104 @@ 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 (
+    int_or_none,
+    NO_DEFAULT,
+    parse_duration,
+    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|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',
         'info_dict': {
             'id': '1740434',
             'display_id': 'hot-perky-blonde-naked-golf',
             'ext': 'mp4',
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {
             'id': '1740434',
             'display_id': 'hot-perky-blonde-naked-golf',
             'ext': 'mp4',

-            'title': 'Hot Perky Blonde Naked Golf',
+            'title': 'hot perky blonde naked golf',

             'like_count': int,
             '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,
+    }, {
+        'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
+        '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(
+            'http://www.drtuber.com/video/%s' % video_id, display_id)

 
 

-        webpage = self._download_webpage(url, display_id)
+        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,
+            })

 
 

-        video_url = self._html_search_regex(
-            r'<source src="([^"]+)"', webpage, 'video URL')
+        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'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+            (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')

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

-        like_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        dislike_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        comment_count = str_to_int(self._html_search_regex(
-            r'<span class="comments_count">([\d,\.]+)</span>',
-            webpage, 'comment count', fatal=False))
+        def extract_count(id_, name, default=NO_DEFAULT):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, default=default, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
+        comment_count = extract_count('comments_count', 'comment')

 
         cats_str = self._search_regex(
 
         cats_str = self._search_regex(

-            r'<span>Categories:</span><div>(.+?)</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,
             '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,


@@ -67,4 +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,

         }
         }