1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 00:17:43 +00:00
youtube-dl/youtube_dl/extractor/kusi.py

89 lines
3 KiB
Python
Raw Normal View History

2016-02-16 01:30:53 +00:00
# coding: utf-8
from __future__ import unicode_literals
2016-03-04 15:08:47 +00:00
import random
2016-02-16 01:30:53 +00:00
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote_plus
2016-03-04 15:08:47 +00:00
from ..utils import (
int_or_none,
float_or_none,
timeconvert,
update_url_query,
xpath_text,
)
2016-02-16 01:30:53 +00:00
class KUSIIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
_TESTS = [{
2016-08-29 15:54:33 +00:00
'url': 'http://www.kusi.com/story/32849881/turko-files-refused-to-help-it-aint-right',
'md5': '4e76ce8e53660ce9697d06c0ba6fc47d',
2016-02-16 01:30:53 +00:00
'info_dict': {
2016-08-29 15:54:33 +00:00
'id': '12689020',
2016-02-16 01:30:53 +00:00
'ext': 'mp4',
2016-08-29 15:54:33 +00:00
'title': "Turko Files: Refused to Help, It Ain't Right!",
'duration': 223.586,
'upload_date': '20160826',
'timestamp': 1472233118,
'thumbnail': r're:^https?://.*\.jpg$'
},
}, {
'url': 'http://kusi.com/video?clipId=12203019',
2016-08-29 15:54:33 +00:00
'only_matching': True,
}]
2016-02-16 01:30:53 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2016-03-04 15:08:47 +00:00
clip_id = mobj.group('clipId')
video_id = clip_id or mobj.group('path')
2016-02-16 01:30:53 +00:00
2016-03-04 15:08:47 +00:00
webpage = self._download_webpage(url, video_id)
2016-02-16 01:30:53 +00:00
2016-03-04 15:08:47 +00:00
if clip_id is None:
video_id = clip_id = self._html_search_regex(
r'"clipId"\s*,\s*"(\d+)"', webpage, 'clip id')
2016-02-16 01:30:53 +00:00
2016-03-04 15:08:47 +00:00
affiliate_id = self._search_regex(
r'affiliateId\s*:\s*\'([^\']+)\'', webpage, 'affiliate id')
# See __Packages/worldnow/model/GalleryModel.as of WNGallery.swf
xml_url = update_url_query('http://www.kusi.com/build.asp', {
'buildtype': 'buildfeaturexmlrequest',
'featureType': 'Clip',
'featureid': clip_id,
'affiliateno': affiliate_id,
'clientgroupid': '1',
'rnd': int(round(random.random() * 1000000)),
})
doc = self._download_xml(xml_url, video_id)
video_title = xpath_text(doc, 'HEADLINE', fatal=True)
duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000)
description = xpath_text(doc, 'ABSTRACT')
thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME')
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 15:00:05 +00:00
creation_time = timeconvert(xpath_text(doc, 'rfc822creationdate'))
2016-02-16 01:30:53 +00:00
quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content')
formats = []
for quality in quality_options:
2016-03-04 15:08:47 +00:00
formats.append({
'url': compat_urllib_parse_unquote_plus(quality.attrib['url']),
'height': int_or_none(quality.attrib.get('height')),
'width': int_or_none(quality.attrib.get('width')),
'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000),
2016-03-04 15:08:47 +00:00
})
2016-02-16 01:30:53 +00:00
self._sort_formats(formats)
return {
'id': video_id,
'title': video_title,
'description': description,
'duration': duration,
'formats': formats,
2016-03-04 15:08:47 +00:00
'thumbnail': thumbnail,
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 15:00:05 +00:00
'timestamp': creation_time,
2016-02-16 01:30:53 +00:00
}