1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 20:48:04 +01:00
youtube-dl/youtube_dl/extractor/ellentv.py

85 lines
2.6 KiB
Python
Raw Normal View History

2014-08-13 12:14:44 +02:00
# coding: utf-8
from __future__ import unicode_literals
import json
2014-08-21 11:57:03 +02:00
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
2014-08-13 12:14:44 +02:00
class EllenTVIE(InfoExtractor):
2015-01-03 16:44:47 +01:00
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
2015-04-24 18:07:15 +02:00
_TEST = {
2015-04-04 20:01:55 +02:00
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
2014-08-13 12:14:44 +02:00
'info_dict': {
2015-04-24 18:07:15 +02:00
'id': '0_ipq1gsai',
2014-08-13 12:14:44 +02:00
'ext': 'mp4',
2015-04-04 20:01:55 +02:00
'title': 'Fast Fingers of Fate',
2015-04-24 18:07:15 +02:00
'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
'timestamp': 1428035648,
2015-04-04 20:01:55 +02:00
'upload_date': '20150403',
2015-04-24 18:07:15 +02:00
'uploader_id': 'batchUser',
2014-08-13 12:14:44 +02:00
}
2015-04-24 18:07:15 +02:00
}
2014-08-13 12:14:44 +02:00
def _real_extract(self, url):
2015-01-03 16:44:47 +01:00
video_id = self._match_id(url)
2014-08-13 12:14:44 +02:00
2015-04-24 18:03:14 +02:00
webpage = self._download_webpage(
'http://widgets.ellentube.com/videos/%s' % video_id,
video_id)
2015-04-24 18:03:14 +02:00
partner_id = self._search_regex(
r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
2014-08-13 12:14:44 +02:00
2015-04-24 18:03:14 +02:00
kaltura_id = self._search_regex(
[r'id="kaltura_player_([^"]+)"',
r"_wb_entry_id\s*:\s*'([^']+)",
r'data-kaltura-entry-id="([^"]+)'],
webpage, 'kaltura id')
return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
2014-08-13 12:14:44 +02:00
2014-08-21 11:57:03 +02:00
2014-08-13 12:14:44 +02:00
class EllenTVClipsIE(InfoExtractor):
2014-08-21 11:57:03 +02:00
IE_NAME = 'EllenTV:clips'
2014-08-13 12:14:44 +02:00
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
_TEST = {
'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
'info_dict': {
2014-08-21 11:57:03 +02:00
'id': 'meryl-streep-vanessa-hudgens',
'title': 'Meryl Streep, Vanessa Hudgens',
},
2015-04-24 18:10:27 +02:00
'playlist_mincount': 7,
2014-08-13 12:14:44 +02:00
}
def _real_extract(self, url):
2015-01-03 16:44:47 +01:00
playlist_id = self._match_id(url)
2014-08-13 12:14:44 +02:00
webpage = self._download_webpage(url, playlist_id)
playlist = self._extract_playlist(webpage)
return {
'_type': 'playlist',
'id': playlist_id,
'title': self._og_search_title(webpage),
'entries': self._extract_entries(playlist)
}
def _extract_playlist(self, webpage):
json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
try:
return json.loads("[{" + json_string + "}]")
except ValueError as ve:
raise ExtractorError('Failed to download JSON', cause=ve)
def _extract_entries(self, playlist):
2015-04-24 18:09:54 +02:00
return [
self.url_result(
'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
'Kaltura')
for item in playlist]