v/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2020-11-18 19:53:54 -08:00
Code Issues Releases Wiki Activity

[slutload] Fix extraction for desktop and mobile site

Browse Source 
Did a separate extractor for the mobile site,
because its structure differs from the desktop site.
This commit is contained in:
Gabor Miklos 2018-07-18 12:33:06 +03:00
parent 79367a9820
commit dbd71aa288
2 changed files with 54 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/extractors.py
View File

@ -988,7 +988,10 @@ from .skynewsarabia import (
from .skysports import SkySportsIE
from .slideshare import SlideshareIE
from .slideslive import SlidesLiveIE
from .slutload import SlutloadIE
from .slutload import (
SlutloadIE,
SlutloadMobileIE
)
from .smotri import (
SmotriIE,
SmotriCommunityIE,

67
youtube_dl/extractor/slutload.py
View File

@ -1,13 +1,11 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class SlutloadIE(InfoExtractor):
_VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
_TESTS = [{
_VALID_URL = r'^https?://(?:www\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
_TEST = {
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
'md5': '868309628ba00fd488cf516a113fd717',
'info_dict': {
@ -17,27 +15,62 @@ class SlutloadIE(InfoExtractor):
'age_limit': 18,
'thumbnail': r're:https?://.*?\.jpg'
}
}, {
# mobile site
'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
'only_matching': True,
}]
}
def _real_extract(self, url):
video_id = self._match_id(url)
desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url)
webpage = self._download_webpage(desktop_url, video_id)
video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
webpage, 'title').strip()
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(
r'<h1><strong>([^<]+)</strong>',
webpage, 'title').strip()
video_url = self._html_search_regex(
r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
r'(?s)<video id=["\']desktop-player["\'].+?<source src=["\']([^"\']+)["\']',
webpage, 'video URL')
thumbnail = self._html_search_regex(
r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
webpage, 'thumbnail', fatal=False)
r'(?s)<video id=["\']desktop-player["\'].+?poster=["\']([^"\']+)["\']',
webpage, 'thumbnail, fatal=False'
)
return {
'id': video_id,
'url': video_url,
'title': video_title,
'thumbnail': thumbnail,
'age_limit': 18
}
class SlutloadMobileIE(InfoExtractor):
_VALID_URL = r'^https?://mobile\.slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
_TEST = {
'url': 'http://mobile.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
'md5': '868309628ba00fd488cf516a113fd717',
'info_dict': {
'id': 'TD73btpBqSxc',
'ext': 'mp4',
'age_limit': 18,
'title': 'virginie baisee en cam',
'thumbnail': r're:https?://.*?\.jpg'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(
r'<div class=["\']videoHd[^"\']+["\']>([^<]+)</div>',
webpage, 'title').strip()
video_url = self._html_search_regex(
r'(?s)<video id=["\']html5video["\'].+?src=["\']([^"\']+)["\']',
webpage, 'video URL')
thumbnail = self._html_search_regex(
r'(?s)<video id=["\']html5video["\'].+?poster=["\']([^"\']+)["\']',
webpage, 'thumbnail, fatal=False'
)
return {
'id': video_id,