kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[zdf] Fix podcast extraction and use unicode literals (Closes #2446)

Browse source
This commit is contained in:
Sergey M. 2014-02-24 13:47:47 +07:00
parent a2dafe2887
commit 919052d094
1 changed files with 34 additions and 36 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

70
youtube_dl/extractor/zdf.py
View file

@ -1,4 +1,5 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import re import re
@ -13,52 +14,42 @@ class ZDFIE(InfoExtractor):
_VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
_TEST = { _TEST = {
u"url": u"http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt", 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
u"file": u"2037704.webm", 'info_dict': {
u"info_dict": { 'id': '2037704',
u"upload_date": u"20131127", 'ext': 'webm',
u"description": u"Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial \"Ende des Machtpokers - Große Koalition für Deutschland\".", 'title': 'ZDFspezial - Ende des Machtpokers',
u"uploader": u"spezial", 'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".',
u"title": u"ZDFspezial - Ende des Machtpokers" 'duration': 1022,
'uploader': 'spezial',
'uploader_id': '225948',
'upload_date': '20131127',
}, },
u"skip": u"Videos on ZDF.de are depublicised in short order", 'skip': 'Videos on ZDF.de are depublicised in short order',
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id') video_id = mobj.group('video_id')
xml_url = u'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
doc = self._download_xml( doc = self._download_xml(
xml_url, video_id, xml_url, video_id,
note=u'Downloading video info', note='Downloading video info',
errnote=u'Failed to download video info') errnote='Failed to download video info')
title = doc.find('.//information/title').text title = doc.find('.//information/title').text
description = doc.find('.//information/detail').text description = doc.find('.//information/detail').text
duration = int(doc.find('.//details/lengthSec').text)
uploader_node = doc.find('.//details/originChannelTitle') uploader_node = doc.find('.//details/originChannelTitle')
uploader = None if uploader_node is None else uploader_node.text uploader = None if uploader_node is None else uploader_node.text
duration_str = doc.find('.//details/length').text uploader_id_node = doc.find('.//details/originChannelId')
duration_m = re.match(r'''(?x)^ uploader_id = None if uploader_id_node is None else uploader_id_node.text
(?P<hours>[0-9]{2})
:(?P<minutes>[0-9]{2})
:(?P<seconds>[0-9]{2})
(?:\.(?P<ms>[0-9]+)?)
''', duration_str)
duration = (
(
(int(duration_m.group('hours')) * 60 * 60) +
(int(duration_m.group('minutes')) * 60) +
int(duration_m.group('seconds'))
)
if duration_m
else None
)
upload_date = unified_strdate(doc.find('.//details/airtime').text) upload_date = unified_strdate(doc.find('.//details/airtime').text)
def xml_to_format(fnode): def xml_to_format(fnode):
video_url = fnode.find('url').text video_url = fnode.find('url').text
is_available = u'http://www.metafilegenerator' not in video_url is_available = 'http://www.metafilegenerator' not in video_url
format_id = fnode.attrib['basetype'] format_id = fnode.attrib['basetype']
format_m = re.match(r'''(?x) format_m = re.match(r'''(?x)
@ -71,22 +62,28 @@ class ZDFIE(InfoExtractor):
quality = fnode.find('./quality').text quality = fnode.find('./quality').text
abr = int(fnode.find('./audioBitrate').text) // 1000 abr = int(fnode.find('./audioBitrate').text) // 1000
vbr = int(fnode.find('./videoBitrate').text) // 1000 vbr_node = fnode.find('./videoBitrate')
vbr = None if vbr_node is None else int(vbr_node.text) // 1000
format_note = u'' width_node = fnode.find('./width')
width = None if width_node is None else int_or_none(width_node.text)
height_node = fnode.find('./height')
height = None if height_node is None else int_or_none(height_node.text)
format_note = ''
if not format_note: if not format_note:
format_note = None format_note = None
return { return {
'format_id': format_id + u'-' + quality, 'format_id': format_id + '-' + quality,
'url': video_url, 'url': video_url,
'ext': ext, 'ext': ext,
'acodec': format_m.group('acodec'), 'acodec': format_m.group('acodec'),
'vcodec': format_m.group('vcodec'), 'vcodec': format_m.group('vcodec'),
'abr': abr, 'abr': abr,
'vbr': vbr, 'vbr': vbr,
'width': int_or_none(fnode.find('./width').text), 'width': width,
'height': int_or_none(fnode.find('./height').text), 'height': height,
'filesize': int_or_none(fnode.find('./filesize').text), 'filesize': int_or_none(fnode.find('./filesize').text),
'format_note': format_note, 'format_note': format_note,
'protocol': proto, 'protocol': proto,
@ -103,9 +100,10 @@ class ZDFIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'formats': formats,
'description': description, 'description': description,
'uploader': uploader,
'duration': duration, 'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'upload_date': upload_date, 'upload_date': upload_date,
} 'formats': formats,
}