github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-25 11:12:11 +00:00
Code Issues Projects Releases Packages Wiki Activity

[itv:btcc] Add extractor (closes #16139)

Browse source
This commit is contained in:
Sergey M․ 2018-05-02 07:21:24 +07:00
parent 5f95927a62
commit ea1f5e5dbd
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 41 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/extractors.py
View file

@ -477,7 +477,10 @@
from .iprima import IPrimaIE
from .iqiyi import IqiyiIE
from .ir90tv import Ir90TvIE
from .itv import ITVIE
from .itv import (
ITVIE,
ITVBTCCIE,
)
from .ivi import (
IviIE,
IviCompilationIE

37
youtube_dl/extractor/itv.py
View file

@ -7,6 +7,7 @@
import re
from .common import InfoExtractor
from .brightcove import BrightcoveNewIE
from ..compat import (
compat_str,
compat_etree_register_namespace,
@ -18,6 +19,7 @@
xpath_text,
int_or_none,
parse_duration,
smuggle_url,
ExtractorError,
determine_ext,
)
@ -260,3 +262,38 @@ def extract_subtitle(sub_url):
'subtitles': subtitles,
})
return info
class ITVBTCCIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/btcc/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
'info_dict': {
'id': 'btcc-2018-all-the-action-from-brands-hatch',
'title': 'BTCC 2018: All the action from Brands Hatch',
},
'playlist_mincount': 9,
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1582188683001/HkiHLnNRx_default/index.html?videoId=%s'
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {
# ITV does not like some GB IP ranges, so here are some
# IP blocks it accepts
'geo_ip_blocks': [
'193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
],
'referrer': url,
}),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
for video_id in re.findall(r'data-video-id=["\'](\d+)', webpage)]
title = self._og_search_title(webpage, fatal=False)
return self.playlist_result(entries, playlist_id, title)