0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 01:35:12 +00:00
yt-dlp/yt_dlp/extractor/caltrans.py
Bricio 0a19532ead
[Caltrans] Add extractor (#2781)
Closes #2775

Authored by: Bricio
2022-02-14 18:45:36 -08:00

41 lines
1.6 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class CaltransIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?ca\.gov/vm/loc/[^/]+/(?P<id>[a-z0-9_]+)\.htm'
_TEST = {
'url': 'https://cwwp2.dot.ca.gov/vm/loc/d3/hwy50at24th.htm',
'info_dict': {
'id': 'hwy50at24th',
'ext': 'ts',
'title': 'US-50 : Sacramento : Hwy 50 at 24th',
'live_status': 'is_live',
'thumbnail': 'https://cwwp2.dot.ca.gov/data/d3/cctv/image/hwy50at24th/hwy50at24th.jpg',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
global_vars = self._search_regex(
r'<script[^<]+?([^<]+\.m3u8[^<]+)</script>',
webpage, 'Global Vars')
route_place = self._search_regex(r'routePlace\s*=\s*"([^"]+)"', global_vars, 'Route Place', fatal=False)
location_name = self._search_regex(r'locationName\s*=\s*"([^"]+)"', global_vars, 'Location Name', fatal=False)
poster_url = self._search_regex(r'posterURL\s*=\s*"([^"]+)"', global_vars, 'Poster Url', fatal=False)
video_stream = self._search_regex(r'videoStreamURL\s*=\s*"([^"]+)"', global_vars, 'Video Stream URL', fatal=False)
formats = self._extract_m3u8_formats(video_stream, video_id, 'ts', live=True)
self._sort_formats(formats)
return {
'id': video_id,
'title': f'{route_place} : {location_name}',
'is_live': True,
'formats': formats,
'thumbnail': poster_url,
}