github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[pornotube] move into own file

Browse source
This commit is contained in:
Philipp Hagemeister 2013-06-23 22:13:32 +02:00
parent 0143dc029c
commit 1183b85f50
2 changed files with 42 additions and 34 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
youtube_dl/InfoExtractors.py
View file

@ -41,6 +41,7 @@
from .extractor.nba import NBAIE from .extractor.nba import NBAIE
from .extractor.statigram import StatigramIE from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE from .extractor.photobucket import PhotobucketIE
from .extractor.pornotube import PornotubeIE
from .extractor.rbmaradio import RBMARadioIE from .extractor.rbmaradio import RBMARadioIE
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.stanfordoc import StanfordOpenClassroomIE
@ -79,40 +80,6 @@
class PornotubeIE(InfoExtractor):
"""Information extractor for pornotube.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
video_title = mobj.group('title')
# Get webpage content
webpage = self._download_webpage(url, video_id)
# Get the video URL
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
video_url = compat_urllib_parse.unquote(video_url)
#Get the uploaded date
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
if upload_date: upload_date = unified_strdate(upload_date)
info = {'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': upload_date,
'title': video_title,
'ext': 'flv',
'format': 'flv'}
return [info]
class YouJizzIE(InfoExtractor): class YouJizzIE(InfoExtractor):
"""Information extractor for youjizz.com.""" """Information extractor for youjizz.com."""

41
youtube_dl/extractor/pornotube.py Normal file
View file

@ -0,0 +1,41 @@
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
unified_strdate,
)
class PornotubeIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
video_title = mobj.group('title')
# Get webpage content
webpage = self._download_webpage(url, video_id)
# Get the video URL
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
video_url = compat_urllib_parse.unquote(video_url)
#Get the uploaded date
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
if upload_date: upload_date = unified_strdate(upload_date)
info = {'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': upload_date,
'title': video_title,
'ext': 'flv',
'format': 'flv'}
return [info]