R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' into DrTuber-issue-12058

Browse Source
This commit is contained in:
Parmjit Virk 2017-06-22 02:36:38 -05:00
commit eb3ce2710a
1 changed files with 33 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
youtube_dl/extractor/youporn.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
sanitized_Request,
@ -26,7 +27,7 @@ class YouPornIE(InfoExtractor):
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ask Dan And Jennifer',
'upload_date': '20101221',
'upload_date': '20101217',
'average_rating': int,
'view_count': int,
'comment_count': int,
@ -45,7 +46,7 @@ class YouPornIE(InfoExtractor):
'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Unknown',
'upload_date': '20111125',
'upload_date': '20110418',
'average_rating': int,
'view_count': int,
'comment_count': int,
@ -68,28 +69,46 @@ class YouPornIE(InfoExtractor):
webpage = self._download_webpage(request, display_id)
title = self._search_regex(
[r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
webpage, 'title', group='title')
[r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'],
webpage, 'title', group='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 = definition.get('videoUrl')
if isinstance(video_url, compat_str) and 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):
r'(?: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):
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'))
@ -124,7 +143,8 @@ 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)