91 lines
3.1 KiB
Python
91 lines
3.1 KiB
Python
|
# coding: utf-8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from .common import InfoExtractor
|
||
|
|
from ..utils import (
|
||
|
|
ExtractorError,
|
||
|
|
float_or_none,
|
||
|
|
int_or_none,
|
||
|
|
parse_iso8601,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
class ClipRsIE(InfoExtractor):
|
||
|
|
_VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+'
|
||
|
|
_TEST = {
|
||
|
|
'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732',
|
||
|
|
'md5': 'c412d57815ba07b56f9edc7b5d6a14e5',
|
||
|
|
'info_dict': {
|
||
|
|
'id': '1488842.1399140381',
|
||
|
|
'ext': 'mp4',
|
||
|
|
'title': 'PREMIJERA Frajle predstavljaju novi spot za pesmu Moli me, moli',
|
||
|
|
'description': 'md5:56ce2c3b4ab31c5a2e0b17cb9a453026',
|
||
|
|
'duration': 229,
|
||
|
|
'timestamp': 1459850243,
|
||
|
|
'upload_date': '20160405',
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
def _real_extract(self, url):
|
||
|
|
video_id = self._match_id(url)
|
||
|
|
|
||
|
|
webpage = self._download_webpage(url, video_id)
|
||
|
|
|
||
|
|
video_id = self._search_regex(
|
||
|
|
r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
|
||
|
|
|
||
|
|
response = self._download_json(
|
||
|
|
'http://qi.ckm.onetapi.pl/', video_id,
|
||
|
|
query={
|
||
|
|
'body[id]': video_id,
|
||
|
|
'body[jsonrpc]': '2.0',
|
||
|
|
'body[method]': 'get_asset_detail',
|
||
|
|
'body[params][ID_Publikacji]': video_id,
|
||
|
|
'body[params][Service]': 'www.onet.pl',
|
||
|
|
'content-type': 'application/jsonp',
|
||
|
|
'x-onet-app': 'player.front.onetapi.pl',
|
||
|
|
})
|
||
|
|
|
||
|
|
error = response.get('error')
|
||
|
|
if error:
|
||
|
|
raise ExtractorError(
|
||
|
|
'%s said: %s' % (self.IE_NAME, error['message']), expected=True)
|
||
|
|
|
||
|
|
video = response['result'].get('0')
|
||
|
|
|
||
|
|
formats = []
|
||
|
|
for _, formats_dict in video['formats'].items():
|
||
|
|
if not isinstance(formats_dict, dict):
|
||
|
|
continue
|
||
|
|
for format_id, format_list in formats_dict.items():
|
||
|
|
if not isinstance(format_list, list):
|
||
|
|
continue
|
||
|
|
for f in format_list:
|
||
|
|
if not f.get('url'):
|
||
|
|
continue
|
||
|
|
formats.append({
|
||
|
|
'url': f['url'],
|
||
|
|
'format_id': format_id,
|
||
|
|
'height': int_or_none(f.get('vertical_resolution')),
|
||
|
|
'width': int_or_none(f.get('horizontal_resolution')),
|
||
|
|
'abr': float_or_none(f.get('audio_bitrate')),
|
||
|
|
'vbr': float_or_none(f.get('video_bitrate')),
|
||
|
|
})
|
||
|
|
self._sort_formats(formats)
|
||
|
|
|
||
|
|
meta = video.get('meta', {})
|
||
|
|
|
||
|
|
title = self._og_search_title(webpage, default=None) or meta['title']
|
||
|
|
description = self._og_search_description(webpage, default=None) or meta.get('description')
|
||
|
|
duration = meta.get('length') or meta.get('lenght')
|
||
|
|
timestamp = parse_iso8601(meta.get('addDate'), ' ')
|
||
|
|
|
||
|
|
return {
|
||
|
|
'id': video_id,
|
||
|
|
'title': title,
|
||
|
|
'description': description,
|
||
|
|
'duration': duration,
|
||
|
|
'timestamp': timestamp,
|
||
|
|
'formats': formats,
|
||
|
|
}
|