Annotate some highlights of the release.

[youtubedl] / youtube_dl / extractor / youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 34ab878a4167580b50ef5b3d5bee94e58b02fe41..e7fca22dec9a17b10ef76efcd43c4b9e0e4da208 100644 (file)
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -5,16 +5,16 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    sanitized_Request,
     str_to_int,
     unescapeHTML,
     unified_strdate,
+    url_or_none,
 )
 from ..aes import aes_decrypt_text
 
 
 class YouPornIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
     _TESTS = [{
         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
@@ -26,7 +26,7 @@ class YouPornIE(InfoExtractor):
             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Ask Dan And Jennifer',
-            'upload_date': '20101221',
+            'upload_date': '20101217',
             'average_rating': int,
             'view_count': int,
             'comment_count': int,
@@ -45,7 +45,7 @@ class YouPornIE(InfoExtractor):
             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Unknown',
-            'upload_date': '20111125',
+            'upload_date': '20110418',
             'average_rating': int,
             'view_count': int,
             'comment_count': int,
@@ -56,40 +56,68 @@ class YouPornIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.youporn.com/watch/505835',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
+            webpage)
+
     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
 
-        request = sanitized_Request(url)
-        request.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(request, display_id)
+        webpage = self._download_webpage(
+            'http://www.youporn.com/watch/%s' % video_id, display_id,
+            headers={'Cookie': 'age_verified=1'})
 
-        title = self._search_regex(
-            [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
-             r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
-            webpage, 'title', group='title')
+        title = self._html_search_regex(
+            r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage, default=None) or self._html_search_meta(
+            'title', webpage, fatal=True)
 
         links = []
 
+        # Main source
+        definitions = self._parse_json(
+            self._search_regex(
+                r'mediaDefinition\s*=\s*(\[.+?\]);', webpage,
+                'media definitions', default='[]'),
+            video_id, fatal=False)
+        if definitions:
+            for definition in definitions:
+                if not isinstance(definition, dict):
+                    continue
+                video_url = url_or_none(definition.get('videoUrl'))
+                if video_url:
+                    links.append(video_url)
+
+        # Fallback #1, this also contains extra low quality 180p format
+        for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
+            links.append(link)
+
+        # Fallback #2 (unavailable as at 22.06.2017)
         sources = self._search_regex(
             r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
         if sources:
             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
                 links.append(link)
 
-        # Fallback #1
+        # Fallback #3 (unavailable as at 22.06.2017)
         for _, link in re.findall(
-                r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
-            links.append(link)
-
-        # Fallback #2, this also contains extra low quality 180p format
-        for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
+                r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
             links.append(link)
 
-        # Fallback #3, encrypted links
+        # Fallback #4, encrypted links (unavailable as at 22.06.2017)
         for _, encrypted_link in re.findall(
                 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
             links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
@@ -115,7 +143,11 @@ class YouPornIE(InfoExtractor):
             formats.append(f)
         self._sort_formats(formats)
 
-        description = self._og_search_description(webpage, default=None)
+        description = self._html_search_regex(
+            r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
+            webpage, 'description',
+            default=None) or self._og_search_description(
+            webpage, default=None)
         thumbnail = self._search_regex(
             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
             webpage, 'thumbnail', fatal=False, group='thumbnail')
@@ -124,7 +156,8 @@ class YouPornIE(InfoExtractor):
             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
             webpage, 'uploader', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
-            r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
+            [r'Date\s+[Aa]dded:\s*<span>([^<]+)',
+             r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
             webpage, 'upload date', fatal=False))
 
         age_limit = self._rta_search(webpage)