Prepare to upload

[youtubedl] / youtube_dl / extractor / youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 9bf8d1eeb741c6fdf189e96ef0ccb0a6b88e2d9d..e7fca22dec9a17b10ef76efcd43c4b9e0e4da208 100644 (file)
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -3,30 +3,30 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import compat_urllib_request

 from ..utils import (
     int_or_none,
     str_to_int,
     unescapeHTML,
     unified_strdate,
 from ..utils import (
     int_or_none,
     str_to_int,
     unescapeHTML,
     unified_strdate,

+    url_or_none,

 )
 from ..aes import aes_decrypt_text
 
 
 class YouPornIE(InfoExtractor):
 )
 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/',
     _TESTS = [{
         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',

-        'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
+        'md5': '3744d24c50438cf5b6f6d59feb5055c2',

         'info_dict': {
             'id': '505835',
             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
             'ext': 'mp4',
             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
         'info_dict': {
             'id': '505835',
             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
             'ext': 'mp4',
             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',

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

             'uploader': 'Ask Dan And Jennifer',
             'uploader': 'Ask Dan And Jennifer',

-            'upload_date': '20101221',
+            'upload_date': '20101217',

             'average_rating': int,
             'view_count': int,
             'comment_count': int,
             'average_rating': int,
             'view_count': int,
             'comment_count': int,


@@ -35,7 +35,7 @@ class YouPornIE(InfoExtractor):
             'age_limit': 18,
         },
     }, {
             'age_limit': 18,
         },
     }, {

-        # Anonymous User uploader
+        # Unknown uploader

         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
         'info_dict': {
             'id': '561726',
         'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
         'info_dict': {
             'id': '561726',


@@ -43,9 +43,9 @@ class YouPornIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Big Tits Awesome Brunette On amazing webcam show',
             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
             'ext': 'mp4',
             'title': 'Big Tits Awesome Brunette On amazing webcam show',
             'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',

-            'thumbnail': 're:^https?://.*\.jpg$',
-            'uploader': 'Anonymous User',
-            'upload_date': '20111125',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Unknown',
+            'upload_date': '20110418',

             'average_rating': int,
             'view_count': int,
             'comment_count': int,
             'average_rating': int,
             'view_count': int,
             'comment_count': int,


@@ -56,40 +56,68 @@ class YouPornIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
         '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')
     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 = compat_urllib_request.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 = []
 
 
         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(
         sources = self._search_regex(

-            r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
+            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)
 
         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(
         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)
 
             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'))
         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'))


@@ -101,8 +129,9 @@ class YouPornIE(InfoExtractor):
             }
             # Video URL's path looks like this:
             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
             }
             # Video URL's path looks like this:
             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4

+            #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4

             # We will benefit from it by extracting some metadata
             # We will benefit from it by extracting some metadata

-            mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
+            mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)

             if mobj:
                 height = int(mobj.group('height'))
                 bitrate = int(mobj.group('bitrate'))
             if mobj:
                 height = int(mobj.group('height'))
                 bitrate = int(mobj.group('bitrate'))


@@ -115,43 +144,46 @@ class YouPornIE(InfoExtractor):
         self._sort_formats(formats)
 
         description = self._html_search_regex(
         self._sort_formats(formats)
 
         description = self._html_search_regex(

-            r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
-            webpage, 'description', default=None)
+            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')
 
         uploader = self._html_search_regex(
         thumbnail = self._search_regex(
             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         uploader = self._html_search_regex(

-            r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
+            r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',

             webpage, 'uploader', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
             webpage, 'uploader', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(

-            r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</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)
 
         average_rating = int_or_none(self._search_regex(
             webpage, 'upload date', fatal=False))
 
         age_limit = self._rta_search(webpage)
 
         average_rating = int_or_none(self._search_regex(

-            r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
+            r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',

             webpage, 'average rating', fatal=False))
 
         view_count = str_to_int(self._search_regex(
             webpage, 'average rating', fatal=False))
 
         view_count = str_to_int(self._search_regex(

-            r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
-            webpage, 'view count', fatal=False))
+            r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
+            webpage, 'view count', fatal=False, group='count'))

         comment_count = str_to_int(self._search_regex(
             r'>All [Cc]omments? \(([\d,.]+)\)',
             webpage, 'comment count', fatal=False))
 
         comment_count = str_to_int(self._search_regex(
             r'>All [Cc]omments? \(([\d,.]+)\)',
             webpage, 'comment count', fatal=False))
 

-        def extract_tag_box(title):
-            tag_box = self._search_regex(
-                (r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*'
-                 '<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title),
-                webpage, '%s tag box' % title, default=None)
+        def extract_tag_box(regex, title):
+            tag_box = self._search_regex(regex, webpage, title, default=None)

             if not tag_box:
                 return []
             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 
             if not tag_box:
                 return []
             return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
 

-        categories = extract_tag_box('Category')
-        tags = extract_tag_box('Tags')
+        categories = extract_tag_box(
+            r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
+        tags = extract_tag_box(
+            r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
+            'tags')

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