1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-29 12:17:41 +00:00
youtube-dl/youtube_dl/extractor/theonion.py

64 lines
2.1 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class TheOnionIE(InfoExtractor):
2015-02-19 03:12:40 +00:00
_VALID_URL = r'https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<id>[0-9]+)/?'
_TEST = {
'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/',
'md5': '19eaa9a39cf9b9804d982e654dc791ee',
'info_dict': {
'id': '2133',
'ext': 'mp4',
'title': 'Man Wearing M&M Jacket Apparently Made In God\'s Image',
'description': 'md5:cc12448686b5600baae9261d3e180910',
'thumbnail': 're:^https?://.*\.jpg\?\d+$',
}
}
def _real_extract(self, url):
2015-02-19 03:12:40 +00:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'"videoId":\s(\d+),', webpage, 'video ID')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage)
formats = []
for src, type_ in sources:
if type_ == 'video/mp4':
formats.append({
'format_id': 'mp4_sd',
'preference': 1,
'url': src,
})
elif type_ == 'video/webm':
formats.append({
'format_id': 'webm_sd',
'preference': 0,
'url': src,
})
elif type_ == 'application/x-mpegURL':
formats.extend(
2015-02-19 03:12:40 +00:00
self._extract_m3u8_formats(src, display_id, preference=-1))
else:
self.report_warning(
'Encountered unexpected format: %s' % type_)
self._sort_formats(formats)
return {
'id': video_id,
2015-02-19 03:12:40 +00:00
'display_id': display_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
}