1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-14 20:59:16 +01:00
yt-dlp/youtube_dl/extractor/rte.py
Jaime Marquínez Ferrándiz 6df7179e6c [rte] Actually recognize https urls
There was a missing 's' before the '?'.
2015-10-17 11:53:59 +02:00

63 lines
2.1 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
)
class RteIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
'info_dict': {
'id': '10478715',
'ext': 'mp4',
'title': 'Watch iWitness online',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
'duration': 60.046,
},
'params': {
'skip_download': 'f4m fails with --test atm'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
description = self._html_search_meta('description', webpage, 'description')
duration = float_or_none(self._html_search_meta(
'duration', webpage, 'duration', fatal=False), 1000)
thumbnail_id = self._search_regex(
r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id
json_string = self._download_json(feeds_url, video_id)
# f4m_url = server + relative_url
f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
f4m_formats = [{
'format_id': f['format_id'],
'url': f['url'],
'ext': 'mp4',
'width': f['width'],
'height': f['height'],
} for f in f4m_formats]
return {
'id': video_id,
'title': title,
'formats': f4m_formats,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
}