laudom/haruhi-dl
2
0
Fork 0
Code Issues 13 Pull requests Packages Projects Releases Wiki Activity

[atttechchannel] fix working, drop flash references

Browse source
This commit is contained in:
Laura Liberda 2020-12-07 04:37:02 +01:00
parent a6102b5483
commit dab3e41041
1 changed files with 12 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
haruhi_dl/extractor/atttechchannel.py
View file

@ -6,22 +6,18 @@ from ..utils import unified_strdate
class ATTTechChannelIE(InfoExtractor):
_VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
_TEST = {
_TESTS = [{
'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'info_dict': {
'id': '11316',
'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'ext': 'flv',
'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
'ext': 'm3u8',
'title': 'AT&T Archives: The UNIX System: Making Computers Easier to Use',
'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140127',
},
'params': {
# rtmp download
'skip_download': True,
},
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
@ -29,16 +25,19 @@ class ATTTechChannelIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r"url\s*:\s*'(rtmp://[^']+)'",
r'(?m)^\s*"src=\'(https?://.+?\.m3u8)\'',
webpage, 'video URL')
video_id = self._search_regex(
r'mediaid\s*=\s*(\d+)',
webpage, 'video id', fatal=False)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
formats = self._extract_m3u8_formats(video_url, video_id)
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
description = self._html_search_meta('description', webpage, 'description')
thumbnail = self._search_regex(r'poster=\'(https?://.+?)\'',
webpage, 'thumbnail', fatal=False)
upload_date = unified_strdate(self._search_regex(
r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
webpage, 'upload date', fatal=False), False)
@ -46,8 +45,7 @@ class ATTTechChannelIE(InfoExtractor):
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': 'flv',
'formats': formats,
'title': title,
'description': description,
'thumbnail': thumbnail,