R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Test; fetch upload date and timestamp

Browse Source
This commit is contained in:
Andrew Udvare 2018-06-10 11:57:40 -04:00
parent 66086f7950
commit b8bd2a22cb
No known key found for this signature in database
GPG Key ID: 1AFD9AFC120C26DD
1 changed files with 26 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/cctv.py
View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from calendar import timegm
from datetime import datetime
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -22,7 +24,6 @@ class CCTVIE(InfoExtractor):
_TESTS = [{ _TESTS = [{
# fo.addVariable("videoCenterId","id") # fo.addVariable("videoCenterId","id")
'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml', 'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
'md5': 'd61ec00a493e09da810bf406a078f691',
'info_dict': { 'info_dict': {
'id': '5ecdbeab623f4973b40ff25f18b174e8', 'id': '5ecdbeab623f4973b40ff25f18b174e8',
'ext': 'mp4', 'ext': 'mp4',
@ -112,6 +113,17 @@ class CCTVIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
'expected_warnings': ['Failed to download m3u8 information'], 'expected_warnings': ['Failed to download m3u8 information'],
}, {
# older multi-part streams, non-HLS
'url': 'http://english.cntv.cn/program/learnchinese/20110325/103360.shtml',
'info_dict': {
'id': '20110325100557_00',
'ext': 'mp4',
'title': 'Learn to Speak Chinese Edition 24-2011 (Chapter 01)',
'duration': 295,
'timestamp': 1301053440,
'upload_date': '20110325',
},
}, { }, {
'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml', 'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
'only_matching': True, 'only_matching': True,
@ -163,6 +175,12 @@ class CCTVIE(InfoExtractor):
data = self._parse_json(data, video_id) data = self._parse_json(data, video_id)
entries = [] entries = []
title = data.get('title') title = data.get('title')
upload_date = self._search_regex(
'<em>(?:\s+)?(\d{2}\-\d{2}\-\d{4}\s+\d{2}\:\d{2})[^<]+',
webpage, 'upload date', fatal=False).strip()
upload_date = re.sub(r'\s+', ' ', upload_date)
udt = datetime.strptime(upload_date, '%m-%d-%Y %H:%M')
for i, chapter in enumerate(data.get('chapters', [])): for i, chapter in enumerate(data.get('chapters', [])):
url = chapter.get('url') url = chapter.get('url')
if title: if title:
@ -170,12 +188,18 @@ class CCTVIE(InfoExtractor):
else: else:
ctitle = 'Chapter %02d' % (i + 1,) ctitle = 'Chapter %02d' % (i + 1,)
if url: if url:
if not url.startswith('http'):
url = re.sub(r'^[^\:]+', 'http', url)
entries.append(dict(id='%s_%02d' % (video_id, i,), entries.append(dict(id='%s_%02d' % (video_id, i,),
thumbnail=data.get('imagePath'), thumbnail=data.get('imagePath'),
title=ctitle, title=ctitle,
duration=int_or_none(chapter.get('duration')), duration=int_or_none(chapter.get('duration')),
upload_date=udt.strftime('%Y%m%d'),
timestamp=timegm(udt.timetuple()),
url=url)) url=url))
return self.playlist_result(entries, playlist_id=video_id, playlist_title=data.get('title')) return self.playlist_result(entries,
playlist_id=video_id,
playlist_title=title)
title = data['title'] title = data['title']