[swrmediathek] improve extraction

This commit is contained in:
Remita Amine 2017-01-06 15:06:08 +01:00
parent 2365f94412
commit a9cd1691b2
1 changed files with 47 additions and 36 deletions

View File

@ -1,10 +1,12 @@
# 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 parse_duration from ..utils import (
parse_duration,
int_or_none,
determine_protocol,
)
class SWRMediathekIE(InfoExtractor): class SWRMediathekIE(InfoExtractor):
@ -38,6 +40,7 @@ class SWRMediathekIE(InfoExtractor):
'uploader': 'SWR Fernsehen', 'uploader': 'SWR Fernsehen',
'uploader_id': '990030', 'uploader_id': '990030',
}, },
'_skip': 'redirect to http://swrmediathek.de/index.htm?hinweis=swrlink',
}, { }, {
'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6', 'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6',
'md5': '4382e4ef2c9d7ce6852535fa867a0dd3', 'md5': '4382e4ef2c9d7ce6852535fa867a0dd3',
@ -51,54 +54,62 @@ class SWRMediathekIE(InfoExtractor):
'upload_date': '20140520', 'upload_date': '20140520',
'uploader': 'SWR 2', 'uploader': 'SWR 2',
'uploader_id': '284670', 'uploader_id': '284670',
} },
'_skip': 'redirect to http://swrmediathek.de/index.htm?hinweis=swrlink',
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
video = self._download_json( video = self._download_json(
'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id, video_id, 'Downloading video JSON') 'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id,
video_id, 'Downloading video JSON')
attr = video['attr'] attr = video['attr']
media_type = attr['entry_etype'] title = attr['entry_title']
media_type = attr.get('entry_etype')
formats = [] formats = []
for entry in video['sub']: for entry in video.get('sub', []):
if entry['name'] != 'entry_media': if entry.get('name') != 'entry_media':
continue continue
entry_attr = entry['attr'] entry_attr = entry.get('attr', {})
codec = entry_attr['val0'] f_url = entry_attr.get('val2')
quality = int(entry_attr['val1']) if not f_url:
continue
fmt = { codec = entry_attr.get('val0')
'url': entry_attr['val2'], if codec == 'm3u8':
'quality': quality, formats.extend(self._extract_m3u8_formats(
} f_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
if media_type == 'Video': elif codec == 'f4m':
fmt.update({ formats.extend(self._extract_f4m_formats(
'format_note': ['144p', '288p', '544p', '720p'][quality - 1], f_url + '?hdcore=3.7.0', video_id,
'vcodec': codec, f4m_id='hds', fatal=False))
else:
formats.append({
'format_id': determine_protocol({'url': f_url}),
'url': f_url,
'quality': int_or_none(entry_attr.get('val1')),
'vcodec': codec if media_type == 'Video' else 'none',
'acodec': codec if media_type == 'Audio' else None,
}) })
elif media_type == 'Audio':
fmt.update({
'acodec': codec,
})
formats.append(fmt)
self._sort_formats(formats) self._sort_formats(formats)
upload_date = None
entry_pdatet = attr.get('entry_pdatet')
if entry_pdatet:
upload_date = entry_pdatet[:-4]
return { return {
'id': video_id, 'id': video_id,
'title': attr['entry_title'], 'title': title,
'description': attr['entry_descl'], 'description': attr.get('entry_descl'),
'thumbnail': attr['entry_image_16_9'], 'thumbnail': attr.get('entry_image_16_9'),
'duration': parse_duration(attr['entry_durat']), 'duration': parse_duration(attr.get('entry_durat')),
'upload_date': attr['entry_pdatet'][:-4], 'upload_date': upload_date,
'uploader': attr['channel_title'], 'uploader': attr.get('channel_title'),
'uploader_id': attr['channel_idkey'], 'uploader_id': attr.get('channel_idkey'),
'formats': formats, 'formats': formats,
} }