mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-12-23 16:36:48 +00:00
[gputechconf] Add new extractor(closes #5775)
This commit is contained in:
parent
dd85e4d707
commit
ec6504b39c
@ -235,6 +235,7 @@ from .golem import GolemIE
|
|||||||
from .googleplus import GooglePlusIE
|
from .googleplus import GooglePlusIE
|
||||||
from .googlesearch import GoogleSearchIE
|
from .googlesearch import GoogleSearchIE
|
||||||
from .goshgay import GoshgayIE
|
from .goshgay import GoshgayIE
|
||||||
|
from .gputechconf import GPUTechConfIE
|
||||||
from .groupon import GrouponIE
|
from .groupon import GrouponIE
|
||||||
from .hark import HarkIE
|
from .hark import HarkIE
|
||||||
from .hearthisat import HearThisAtIE
|
from .hearthisat import HearThisAtIE
|
||||||
|
57
youtube_dl/extractor/gputechconf.py
Normal file
57
youtube_dl/extractor/gputechconf.py
Normal file
@ -0,0 +1,57 @@
|
|||||||
|
# coding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
xpath_element,
|
||||||
|
xpath_text,
|
||||||
|
int_or_none,
|
||||||
|
parse_duration,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class GPUTechConfIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://on-demand\.gputechconf\.com/gtc/2015/video/S(?P<id>\d+)\.html'
|
||||||
|
_TEST = {
|
||||||
|
'url': 'http://on-demand.gputechconf.com/gtc/2015/video/S5156.html',
|
||||||
|
'md5': 'a8862a00a0fd65b8b43acc5b8e33f798',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '5156',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Coordinating More Than 3 Million CUDA Threads for Social Network Analysis',
|
||||||
|
'duration': 1219,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
|
root_path = self._search_regex(r'var\s+rootPath\s*=\s*"([^"]+)', webpage, 'root path', 'http://evt.dispeak.com/nvidia/events/gtc15/')
|
||||||
|
xml_file_id = self._search_regex(r'var\s+xmlFileId\s*=\s*"([^"]+)', webpage, 'xml file id')
|
||||||
|
|
||||||
|
doc = self._download_xml('%sxml/%s.xml' % (root_path, xml_file_id), video_id)
|
||||||
|
|
||||||
|
metadata = xpath_element(doc, 'metadata')
|
||||||
|
http_host = xpath_text(metadata, 'httpHost')
|
||||||
|
mbr_videos = xpath_element(metadata, 'MBRVideos')
|
||||||
|
|
||||||
|
formats = []
|
||||||
|
for mbr_video in mbr_videos.findall('MBRVideo'):
|
||||||
|
stream_name = xpath_text(mbr_video, 'streamName')
|
||||||
|
if stream_name:
|
||||||
|
bitrate = int_or_none(xpath_text(mbr_video, 'bitrate'))
|
||||||
|
formats.append({
|
||||||
|
'url': 'http://%s/%s' % (http_host, stream_name.replace('mp4:', '')),
|
||||||
|
'tbr': bitrate,
|
||||||
|
'format_id': 'http-%d' % bitrate,
|
||||||
|
})
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'title': xpath_text(metadata, 'title'),
|
||||||
|
'duration': parse_duration(xpath_text(metadata, 'endTime')),
|
||||||
|
'creator': xpath_text(metadata, 'speaker'),
|
||||||
|
'formats': formats,
|
||||||
|
}
|
Loading…
Reference in New Issue
Block a user