yt-dlp/youtube_dl/extractor/iprima.py

97 lines
3.2 KiB
Python
Raw Normal View History

2016-03-24 17:54:26 +01:00
# coding: utf-8
from __future__ import unicode_literals
import re
2016-02-06 21:23:41 +01:00
import time
from .common import InfoExtractor
from ..utils import (
2016-03-24 17:54:26 +01:00
determine_ext,
js_to_json,
2014-03-14 19:38:44 +01:00
)
class IPrimaIE(InfoExtractor):
2016-02-06 21:23:41 +01:00
_VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
_TESTS = [{
2016-02-06 21:23:41 +01:00
'url': 'http://play.iprima.cz/gondici-s-r-o-33',
'info_dict': {
2016-02-06 21:23:41 +01:00
'id': 'p136534',
'ext': 'mp4',
'title': 'Gondíci s. r. o. (34)',
'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
},
'params': {
2016-02-06 21:23:41 +01:00
'skip_download': True, # m3u8 download
},
}, {
2016-02-06 21:23:41 +01:00
'url': 'http://play.iprima.cz/particka/particka-92',
2015-06-02 12:16:58 +02:00
'only_matching': True,
}]
def _real_extract(self, url):
2016-03-24 17:54:26 +01:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2016-02-06 21:23:41 +01:00
video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id')
2014-03-14 19:38:44 +01:00
2017-02-20 17:16:14 +01:00
playerpage = self._download_webpage(
'http://play.iprima.cz/prehravac/init',
video_id, note='Downloading player', query={
'_infuse': 1,
'_ts': round(time.time()),
'productId': video_id,
}, headers={'Referer': url})
2016-03-24 17:54:26 +01:00
formats = []
2016-03-24 17:54:26 +01:00
def extract_formats(format_url, format_key=None, lang=None):
ext = determine_ext(format_url)
new_formats = []
if format_key == 'hls' or ext == 'm3u8':
new_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
elif format_key == 'dash' or ext == 'mpd':
return
new_formats = self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False)
if lang:
for f in new_formats:
if not f.get('language'):
f['language'] = lang
formats.extend(new_formats)
options = self._parse_json(
self._search_regex(
r'(?s)(?:TDIPlayerOptions|playerOptions)\s*=\s*({.+?});\s*\]\]',
2016-03-24 17:54:26 +01:00
playerpage, 'player options', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if options:
for key, tracks in options.get('tracks', {}).items():
if not isinstance(tracks, list):
continue
for track in tracks:
src = track.get('src')
if src:
extract_formats(src, key.lower(), track.get('lang'))
if not formats:
for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
extract_formats(src)
2016-10-07 16:53:03 +02:00
if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
self.raise_geo_restricted()
self._sort_formats(formats)
return {
2016-02-06 21:23:41 +01:00
'id': video_id,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
2016-02-06 21:23:41 +01:00
'description': self._og_search_description(webpage),
}