mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-01 23:12:40 +00:00
[TheChiveIE] added support for TheChive.com (Closes #5016)
This commit is contained in:
parent
250a9bdfe2
commit
1a2313a6f2
2 changed files with 61 additions and 0 deletions
|
@ -481,6 +481,7 @@
|
|||
from .testurl import TestURLIE
|
||||
from .testtube import TestTubeIE
|
||||
from .tf1 import TF1IE
|
||||
from .thechive import TheChiveIE
|
||||
from .theonion import TheOnionIE
|
||||
from .theplatform import ThePlatformIE
|
||||
from .thesixtyone import TheSixtyOneIE
|
||||
|
|
60
youtube_dl/extractor/thechive.py
Normal file
60
youtube_dl/extractor/thechive.py
Normal file
|
@ -0,0 +1,60 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
|
||||
|
||||
|
||||
class TheChiveIE(InfoExtractor):
|
||||
_VALID_URL = r'http://(www\.)?thechive\.com/[^/]+/[^/]+/[^/]+/(?P<video_id>[A-Za-z\-]+)'
|
||||
_TEST = {
|
||||
'url': "http://thechive.com/2015/02/20/so-thats-what-a-set-of-redneck-bagpipes-sound-like-video/",
|
||||
'md5': "366710dda77cfa727bdef3523ba8466f",
|
||||
'info_dict': {
|
||||
'id': "so-thats-what-a-set-of-redneck-bagpipes-sound-like-video",
|
||||
'title': "So that's what a set of redneck bagpipes sound like... (Video)",
|
||||
'description': "Okay that was pretty good. Now play Freebird!...",
|
||||
'thumbnail': "https://thechive.files.wordpress.com/2015/02/0_07dghz0w-thumbnail2.jpg",
|
||||
'author': "Ben",
|
||||
'upload_date': "20150220",
|
||||
'ext': "mp4"
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._html_search_regex(r'(?s)<meta name="description" content="(.*?)" />', webpage, 'description')
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
author = self._html_search_regex(
|
||||
r'(?s)itemprop="author">(.+?)</span>', webpage, 'author', fatal=False).capitalize()
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'(?s)itemprop="datePublished" datetime="(.+?)">', webpage, 'upload_date', fatal=False))
|
||||
|
||||
# Adapted from extractor/musicvault.py
|
||||
VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http'
|
||||
|
||||
kaltura_id = self._search_regex(
|
||||
r'entry_id=([^"]+)',
|
||||
webpage, 'kaltura ID')
|
||||
video_url = VIDEO_URL_TEMPLATE % {
|
||||
'entry_id': kaltura_id,
|
||||
'wid': self._search_regex(r'partner_id/([0-9]+)\?', webpage, 'wid'),
|
||||
'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'),
|
||||
}
|
||||
|
||||
return {
|
||||
'url': video_url,
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'author': author,
|
||||
'upload_date': upload_date,
|
||||
'ext': 'mp4'
|
||||
}
|
Loading…
Reference in a new issue