yt-dlc/youtube_dl/extractor/heise.py

80 lines
2.8 KiB
Python
Raw Normal View History

2014-09-27 19:28:01 +02:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
2014-09-27 19:28:01 +02:00
parse_iso8601,
)
class HeiseIE(InfoExtractor):
2014-09-28 10:40:49 +02:00
_VALID_URL = r'''(?x)
https?://(?:www\.)?heise\.de/video/artikel/
.+?(?P<id>[0-9]+)\.html(?:$|[?#])
'''
2014-09-27 19:28:01 +02:00
_TEST = {
'url': (
2014-09-28 10:40:49 +02:00
'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
2014-09-27 19:28:01 +02:00
),
'md5': 'ffed432483e922e88545ad9f2f15d30e',
'info_dict': {
'id': '2404147',
'ext': 'mp4',
'title': (
2014-09-28 10:40:49 +02:00
"Podcast: c't uplink 3.3 Owncloud / Tastaturen / Peilsender Smartphone"
2014-09-27 19:28:01 +02:00
),
'format_id': 'mp4_720p',
2014-09-27 19:28:01 +02:00
'timestamp': 1411812600,
'upload_date': '20140927',
2014-09-28 10:49:12 +02:00
'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
'thumbnail': 're:^https?://.*\.jpe?g$',
2014-09-27 19:28:01 +02:00
}
}
def _real_extract(self, url):
2014-09-28 10:40:49 +02:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
container_id = self._search_regex(
r'<div class="videoplayerjw".*?data-container="([0-9]+)"',
webpage, 'container ID')
sequenz_id = self._search_regex(
r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"',
webpage, 'sequenz ID')
data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id)
doc = self._download_xml(data_url, video_id)
2014-09-27 19:28:01 +02:00
info = {
2014-09-28 10:40:49 +02:00
'id': video_id,
'thumbnail': self._og_search_thumbnail(webpage),
'timestamp': parse_iso8601(
self._html_search_meta('date', webpage)),
2014-09-28 10:49:12 +02:00
'description': self._og_search_description(webpage),
2014-09-27 19:28:01 +02:00
}
title = self._html_search_meta('fulltitle', webpage)
2014-09-27 19:28:01 +02:00
if title:
info['title'] = title
else:
2014-09-28 10:40:49 +02:00
info['title'] = self._og_search_title(webpage)
2014-09-27 19:28:01 +02:00
formats = []
for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
label = source_node.attrib['label']
height = int_or_none(self._search_regex(
r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
video_url = source_node.attrib['file']
ext = determine_ext(video_url, '')
formats.append({
'url': video_url,
'format_note': label,
'format_id': '%s_%s' % (ext, label),
'height': height,
})
2014-09-27 19:28:01 +02:00
self._sort_formats(formats)
info['formats'] = formats
return info