ytdl-nightly/youtube_dl/extractor/ellentv.py

95 lines
3.2 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,
parse_iso8601,
)
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_-]+)'
_TESTS = [{
2014-08-13 12:14:44 +02:00
'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
'md5': 'e4af06f3bf0d5f471921a18db5764642',
'info_dict': {
'id': '0-7jqrsr18',
'ext': 'mp4',
2014-08-21 11:57:03 +02:00
'title': 'What\'s Wrong with These Photos? A Whole Lot',
2015-01-03 16:54:18 +01:00
'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
2014-08-21 11:57:03 +02:00
'timestamp': 1406876400,
'upload_date': '20140801',
2014-08-13 12:14:44 +02:00
}
2015-01-03 16:44:47 +01:00
}, {
'url': 'http://ellentube.com/videos/0-dvzmabd5/',
'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
'info_dict': {
'id': '0-dvzmabd5',
'ext': 'mp4',
'title': '1 year old twin sister makes her brother laugh',
2015-01-03 16:54:18 +01:00
'description': '1 year old twin sister makes her brother laugh',
'timestamp': 1419542075,
'upload_date': '20141225',
}
}]
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
2014-08-21 11:57:03 +02:00
webpage = self._download_webpage(url, video_id)
2015-01-03 16:54:18 +01:00
video_url = self._html_search_meta('VideoURL', webpage, 'url')
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
description = self._html_search_meta(
'description', webpage, 'description') or self._og_search_description(webpage)
2014-08-21 11:57:03 +02:00
timestamp = parse_iso8601(self._search_regex(
r'<span class="publish-date"><time datetime="([^"]+)">',
webpage, 'timestamp'))
2014-08-13 12:14:44 +02:00
return {
2014-08-21 11:57:03 +02:00
'id': video_id,
2015-01-03 16:54:18 +01:00
'url': video_url,
'title': title,
'description': description,
2014-08-21 11:57:03 +02:00
'timestamp': timestamp,
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',
},
'playlist_mincount': 9,
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):
2014-08-21 11:57:03 +02:00
return [self.url_result(item['url'], 'EllenTV') for item in playlist]