[heise] Simplify (#3842)

This commit is contained in:
Philipp Hagemeister 2014-09-28 10:40:49 +02:00
parent 0217aee154
commit 5a8b77551d

View File

@ -1,34 +1,28 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
compat_urllib_parse,
get_meta_content, get_meta_content,
parse_iso8601, parse_iso8601,
) )
class HeiseIE(InfoExtractor): class HeiseIE(InfoExtractor):
_VALID_URL = ( _VALID_URL = r'''(?x)
r'^https?://(?:www\.)?heise\.de/video/artikel/' + https?://(?:www\.)?heise\.de/video/artikel/
r'.+?(?P<id>[0-9]+)\.html$' .+?(?P<id>[0-9]+)\.html(?:$|[?#])
) '''
_TEST = { _TEST = {
'url': ( 'url': (
'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-' + 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
'Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
), ),
'md5': 'ffed432483e922e88545ad9f2f15d30e', 'md5': 'ffed432483e922e88545ad9f2f15d30e',
'info_dict': { 'info_dict': {
'id': '2404147', 'id': '2404147',
'ext': 'mp4', 'ext': 'mp4',
'title': ( 'title': (
"Podcast: c't uplink 3.3 Owncloud / Tastaturen / " + "Podcast: c't uplink 3.3 Owncloud / Tastaturen / Peilsender Smartphone"
"Peilsender Smartphone"
), ),
'format_id': 'mp4_720', 'format_id': 'mp4_720',
'timestamp': 1411812600, 'timestamp': 1411812600,
@ -36,84 +30,50 @@ class HeiseIE(InfoExtractor):
} }
} }
_CONFIG = (
r'".+?\?sequenz=(?P<sequenz>.+?)&container=(?P<container>.+?)' +
r'(?:&hd=(?P<hd>.+?))?(?:&signature=(?P<signature>.+?))?&callback=\?"'
)
_PREFIX = 'http://www.heise.de/videout/info?'
def _warn(self, fmt, *args):
self.report_warning(fmt.format(*args), self._id)
def _parse_config_url(self, html):
m = re.search(self._CONFIG, html)
if not m:
raise ExtractorError('No config found')
qs = compat_urllib_parse.urlencode(dict((k, v) for k, v
in m.groupdict().items()
if v is not None))
return self._PREFIX + qs
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
self._id = mobj.group('id')
html = self._download_webpage(url, self._id) webpage = self._download_webpage(url, video_id)
config = self._download_json(self._parse_config_url(html), self._id) json_url = self._search_regex(
r'json_url:\s*"([^"]+)"', webpage, 'json URL')
config = self._download_json(json_url, video_id)
info = { info = {
'id': self._id 'id': video_id,
'thumbnail': config.get('poster'),
'timestamp': parse_iso8601(get_meta_content('date', webpage)),
} }
title = get_meta_content('fulltitle', html) title = get_meta_content('fulltitle', webpage)
if title: if title:
info['title'] = title info['title'] = title
elif config.get('title'): elif config.get('title'):
info['title'] = config['title'] info['title'] = config['title']
else: else:
self._warn('title: not found') info['title'] = self._og_search_title(webpage)
info['title'] = 'heise'
if (not config.get('formats') or
not hasattr(config['formats'], 'items')):
raise ExtractorError('No formats found')
formats = [] formats = []
for t, rs in config['formats'].items(): for t, rs in config['formats'].items():
if not rs or not hasattr(rs, 'items'): if not rs or not hasattr(rs, 'items'):
self._warn('formats: {0}: no resolutions', t) self._downloader.report_warning(
'formats: {0}: no resolutions'.format(t))
continue continue
for res, obj in rs.items(): for height_str, obj in rs.items():
format_id = '{0}_{1}'.format(t, res) format_id = '{0}_{1}'.format(t, height_str)
if not obj or not obj.get('url'): if not obj or not obj.get('url'):
self._warn('formats: {0}: no url', format_id) self._downloader.report_warning(
'formats: {0}: no url'.format(format_id))
continue continue
fmt = { formats.append({
'url': obj['url'], 'url': obj['url'],
'format_id': format_id 'format_id': format_id,
} 'height': self._int(height_str, 'height'),
try: })
fmt['height'] = int(res)
except ValueError as e:
self._warn('formats: {0}: height: {1}', t, e)
formats.append(fmt)
self._sort_formats(formats) self._sort_formats(formats)
info['formats'] = formats info['formats'] = formats
if config.get('poster'):
info['thumbnail'] = config['poster']
date = get_meta_content('date', html)
if date:
try:
info['timestamp'] = parse_iso8601(date)
except ValueError as e:
self._warn('timestamp: {0}', e)
return info return info