Annotate changelog with bug being closed.

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 4e8fbde8d6bbb072e7fc3475288c6c2e93360993..be3624ef2ea889835992e55949271c0028e9783b 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -3,87 +3,165 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
 from ..utils import (

+    clean_html,
+    dict_get,

     ExtractorError,
     ExtractorError,

-    unified_strdate,
-    str_to_int,

     int_or_none,
     parse_duration,
     int_or_none,
     parse_duration,

+    unified_strdate,

 )
 
 
 class XHamsterIE(InfoExtractor):
 )
 
 
 class XHamsterIE(InfoExtractor):

-    """Information Extractor for xHamster"""
-    _VALID_URL = r'http://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
-    _TESTS = [
-        {
-            'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-            'info_dict': {
-                'id': '1509445',
-                'ext': 'mp4',
-                'title': 'FemaleAgent Shy beauty takes the bait',
-                'upload_date': '20121014',
-                'uploader_id': 'Ruseful2011',
-                'duration': 893,
-                'age_limit': 18,
-            }
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:.+?\.)?xhamster\.com/
+                        (?:
+                            movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
+                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
+                        )
+                    '''
+
+    _TESTS = [{
+        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'info_dict': {
+            'id': '1509445',
+            'display_id': 'femaleagent_shy_beauty_takes_the_bait',
+            'ext': 'mp4',
+            'title': 'FemaleAgent Shy beauty takes the bait',
+            'upload_date': '20121014',
+            'uploader': 'Ruseful2011',
+            'duration': 893,
+            'age_limit': 18,
+            'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],

         },
         },

-        {
-            'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-            'info_dict': {
-                'id': '2221348',
-                'ext': 'mp4',
-                'title': 'Britney Spears  Sexy Booty',
-                'upload_date': '20130914',
-                'uploader_id': 'jojo747400',
-                'duration': 200,
-                'age_limit': 18,
-            }
-        }
-    ]
-
-    def _real_extract(self,url):
-        def extract_video_url(webpage):
-            mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
-            if mp4 is None:
-                raise ExtractorError('Unable to extract media URL')
-            else:
-                return mp4.group(1)
-
-        def is_hd(webpage):
-            return '<div class=\'icon iconHD\'' in webpage
-
+    }, {
+        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'info_dict': {
+            'id': '2221348',
+            'display_id': 'britney_spears_sexy_booty',
+            'ext': 'mp4',
+            'title': 'Britney Spears  Sexy Booty',
+            'upload_date': '20130914',
+            'uploader': 'jojo747400',
+            'duration': 200,
+            'age_limit': 18,
+            'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # empty seo
+        'url': 'http://xhamster.com/movies/5667973/.html',
+        'info_dict': {
+            'id': '5667973',
+            'ext': 'mp4',
+            'title': '....',
+            'upload_date': '20160208',
+            'uploader': 'parejafree',
+            'duration': 72,
+            'age_limit': 18,
+            'categories': ['Amateur', 'Blowjobs'],
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
+        'only_matching': True,
+    }, {
+        # This video is visible for marcoalfa123456's friends only
+        'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
+        'only_matching': True,
+    }, {
+        # new URL schema
+        'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):

         mobj = re.match(self._VALID_URL, url)
         mobj = re.match(self._VALID_URL, url)

+        video_id = mobj.group('id') or mobj.group('id_2')
+        display_id = mobj.group('display_id') or mobj.group('display_id_2')
+
+        webpage = self._download_webpage(url, video_id)
+
+        error = self._html_search_regex(
+            r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
+            webpage, 'error', default=None)
+        if error:
+            raise ExtractorError(error, expected=True)
+
+        title = self._html_search_regex(
+            [r'<h1[^>]*>([^<]+)</h1>',
+             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+             r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+            webpage, 'title')
+
+        formats = []
+        format_urls = set()
+
+        sources = self._parse_json(
+            self._search_regex(
+                r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
+                default='{}'),
+            video_id, fatal=False)
+        for format_id, format_url in sources.items():
+            if not isinstance(format_url, compat_str):
+                continue
+            if format_url in format_urls:
+                continue
+            format_urls.add(format_url)
+            formats.append({
+                'format_id': format_id,
+                'url': format_url,
+                'height': int_or_none(self._search_regex(
+                    r'^(\d+)[pP]', format_id, 'height', default=None))
+            })
+
+        video_url = self._search_regex(
+            [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
+             r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
+             r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
+            webpage, 'video url', group='mp4', default=None)
+        if video_url and video_url not in format_urls:
+            formats.append({
+                'url': video_url,
+            })

 
 

-        video_id = mobj.group('id')
-        seo = mobj.group('seo')
-        mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
-        webpage = self._download_webpage(mrss_url, video_id)
-
-        title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
+        self._sort_formats(formats)

 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
         description = mobj.group(1) if mobj else None
 
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
         description = mobj.group(1) if mobj else None
 

-        upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
-            webpage, 'upload date', fatal=False)
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
+        upload_date = unified_strdate(self._search_regex(
+            r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
+            webpage, 'upload date', fatal=False))

 
 

-        uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
-            webpage, 'uploader id', default='anonymous')
+        uploader = self._html_search_regex(
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
+            webpage, 'uploader', default='anonymous')

 
 

-        thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
+        thumbnail = self._search_regex(
+            [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
+             r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
+            webpage, 'thumbnail', fatal=False, group='thumbnail')

 
 

-        duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
-            webpage, 'duration', fatal=False))
+        duration = parse_duration(self._search_regex(
+            [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
+             r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
+            'duration', fatal=False))

 
 

-        view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
-        if view_count:
-            view_count = str_to_int(view_count)
+        view_count = int_or_none(self._search_regex(
+            r'content=["\']User(?:View|Play)s:(\d+)',
+            webpage, 'view count', fatal=False))

 
 

-        mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+        mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)

         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 
         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 
         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)


@@ -91,34 +169,19 @@ class XHamsterIE(InfoExtractor):
 
         age_limit = self._rta_search(webpage)
 
 
         age_limit = self._rta_search(webpage)
 

-        hd = is_hd(webpage)
-
-        video_url = extract_video_url(webpage)
-        formats = [{
-            'url': video_url,
-            'format_id': 'hd' if hd else 'sd',
-            'preference': 1,
-        }]
-
-        if not hd:
-            mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
-            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
-            if is_hd(webpage):
-                video_url = extract_video_url(webpage)
-                formats.append({
-                    'url': video_url,
-                    'format_id': 'hd',
-                    'preference': 2,
-                })
-
-        self._sort_formats(formats)
+        categories_html = self._search_regex(
+            r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
+            'categories', default=None)
+        categories = [clean_html(category) for category in re.findall(
+            r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None

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

+            'display_id': display_id,

             'title': title,
             'description': description,
             'upload_date': upload_date,
             'title': title,
             'description': description,
             'upload_date': upload_date,

-            'uploader_id': uploader_id,
+            'uploader': uploader,

             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,
             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,


@@ -126,5 +189,45 @@ class XHamsterIE(InfoExtractor):
             'dislike_count': int_or_none(dislike_count),
             'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
             'dislike_count': int_or_none(dislike_count),
             'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,

+            'categories': categories,

             'formats': formats,
         }
             'formats': formats,
         }

+
+
+class XHamsterEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://xhamster.com/xembed.php?video=3328539',
+        'info_dict': {
+            'id': '3328539',
+            'ext': 'mp4',
+            'title': 'Pen Masturbation',
+            'upload_date': '20140728',
+            'uploader_id': 'anonymous',
+            'duration': 5,
+            'age_limit': 18,
+        }
+    }
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
+            webpage, 'xhamster url', default=None)
+
+        if not video_url:
+            vars = self._parse_json(
+                self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
+                video_id)
+            video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
+
+        return self.url_result(video_url, 'XHamster')