X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/38bb9b1b0a044cabaf5691553815e334cd2e9213..dbb40c34b0cf975d3c249affe5fc8865fd7a3d5d:/youtube_dl/extractor/xhamster.py
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index b4ad513..7b67037 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,54 +4,73 @@ import re
from .common import InfoExtractor
from ..utils import (
+ dict_get,
ExtractorError,
- unified_strdate,
- str_to_int,
int_or_none,
parse_duration,
+ unified_strdate,
)
class XHamsterIE(InfoExtractor):
- _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?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'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
+ _TESTS = [{
+ 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+ 'md5': '8281348b8d3c53d39fffb377d24eac4e',
+ 'info_dict': {
+ 'id': '1509445',
+ 'ext': 'mp4',
+ 'title': 'FemaleAgent Shy beauty takes the bait',
+ 'upload_date': '20121014',
+ 'uploader': 'Ruseful2011',
+ 'duration': 893,
+ 'age_limit': 18,
},
- {
- '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,
- }
+ }, {
+ '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': 'jojo747400',
+ 'duration': 200,
+ 'age_limit': 18,
},
- {
- 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
- 'only_matching': True,
+ '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,
+ },
+ '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,
+ }]
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 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
@@ -64,28 +83,42 @@ class XHamsterIE(InfoExtractor):
mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, 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')
+ 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')
# 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[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
+ 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'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)
(like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
@@ -97,7 +130,9 @@ class XHamsterIE(InfoExtractor):
hd = is_hd(webpage)
- video_url = extract_video_url(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',
@@ -108,7 +143,7 @@ class XHamsterIE(InfoExtractor):
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)
+ video_url = extract_video_url(webpage, 'hd')
formats.append({
'url': video_url,
'format_id': 'hd',
@@ -122,7 +157,7 @@ class XHamsterIE(InfoExtractor):
'title': title,
'description': description,
'upload_date': upload_date,
- 'uploader_id': uploader_id,
+ 'uploader': uploader,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
@@ -161,7 +196,13 @@ class XHamsterEmbedIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
- r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
- webpage, 'xhamster url')
+ r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % 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')