youtube-dl/youtube_dl/extractor/faz.py

74 lines
2.7 KiB
Python
Raw Normal View History

# encoding: utf-8
2014-10-27 07:11:15 +09:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
xpath_element,
xpath_text,
int_or_none,
)
class FazIE(InfoExtractor):
2014-10-27 07:11:15 +09:00
IE_NAME = 'faz.net'
2015-06-22 23:11:15 +09:00
_VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
2015-06-22 23:11:15 +09:00
_TESTS = [{
2014-10-27 07:11:15 +09:00
'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
'info_dict': {
'id': '12610585',
'ext': 'mp4',
'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
'description': 'md5:1453fbf9a0d041d985a47306192ea253',
},
2015-06-22 23:11:15 +09:00
}, {
'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
'only_matching': True,
}, {
'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
'only_matching': True,
}, {
'url': 'http://www.faz.net/-13659345.html',
'only_matching': True,
}, {
'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
'only_matching': True,
}, {
'url': 'http://www.faz.net/foobarblafasel-13659345.html',
'only_matching': True,
}]
def _real_extract(self, url):
2014-10-27 07:11:15 +09:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
description = self._og_search_description(webpage)
2014-10-27 07:11:15 +09:00
config_xml_url = self._search_regex(
r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
2014-10-27 07:11:15 +09:00
config = self._download_xml(
config_xml_url, video_id, 'Downloading config xml')
encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
formats = []
2014-10-27 07:11:15 +09:00
for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
encoding = xpath_element(encodings, code)
if encoding:
encoding_url = xpath_text(encoding, 'FILENAME')
if encoding_url:
formats.append({
'url': encoding_url,
'format_id': code.lower(),
'quality': pref,
'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
})
2014-10-27 07:11:15 +09:00
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': description.strip() if description else None,
'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
'duration': int_or_none(xpath_text(config, 'DURATION')),
}