debian/control: Update the repository to github.com.

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 7b67037140653cacdc5740f7c560280335de0a0d..be3624ef2ea889835992e55949271c0028e9783b 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -3,7 +3,9 @@ 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,
     int_or_none,
     dict_get,
     ExtractorError,
     int_or_none,


@@ -13,29 +15,41 @@ from ..utils import (
 
 
 class XHamsterIE(InfoExtractor):
 
 
 class XHamsterIE(InfoExtractor):

-    _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
+    _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',
     _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,
             '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',
         },
     }, {
         '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,
             '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,
         },
         'params': {
             'skip_download': True,


@@ -51,6 +65,7 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'parejafree',
             'duration': 72,
             'age_limit': 18,
             'uploader': 'parejafree',
             'duration': 72,
             'age_limit': 18,

+            'categories': ['Amateur', 'Blowjobs'],

         },
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,


@@ -62,26 +77,18 @@ class XHamsterIE(InfoExtractor):
         # This video is visible for marcoalfa123456's friends only
         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.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):
     }]
 
     def _real_extract(self, url):

-        def extract_video_url(webpage, name):
-            return 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, name, group='mp4')
-
-        def is_hd(webpage):
-            return '<div class=\'icon iconHD\'' in webpage
-

         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')

 
 

-        video_id = mobj.group('id')
-        seo = mobj.group('seo')
-        proto = mobj.group('proto')
-        mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
-        webpage = self._download_webpage(mrss_url, video_id)
+        webpage = self._download_webpage(url, video_id)

 
         error = self._html_search_regex(
             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 
         error = self._html_search_regex(
             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',


@@ -95,6 +102,39 @@ class XHamsterIE(InfoExtractor):
              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
             webpage, 'title')
 
              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,
+            })
+
+        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


@@ -104,7 +144,7 @@ class XHamsterIE(InfoExtractor):
             webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(
             webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(

-            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',

             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(
             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(


@@ -113,14 +153,15 @@ class XHamsterIE(InfoExtractor):
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         duration = parse_duration(self._search_regex(
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         duration = parse_duration(self._search_regex(

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

             'duration', fatal=False))
 
         view_count = int_or_none(self._search_regex(
             r'content=["\']User(?:View|Play)s:(\d+)',
             webpage, 'view count', fatal=False))
 
             'duration', fatal=False))
 
         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)


@@ -128,32 +169,15 @@ class XHamsterIE(InfoExtractor):
 
         age_limit = self._rta_search(webpage)
 
 
         age_limit = self._rta_search(webpage)
 

-        hd = is_hd(webpage)
-
-        format_id = 'hd' if hd else 'sd'
-
-        video_url = extract_video_url(webpage, format_id)
-        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, 'hd')
-                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,


@@ -165,6 +189,7 @@ 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,
         }
 


@@ -196,7 +221,7 @@ class XHamsterEmbedIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._search_regex(
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._search_regex(

-            r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
+            r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),

             webpage, 'xhamster url', default=None)
 
         if not video_url:
             webpage, 'xhamster url', default=None)
 
         if not video_url: