yt-dlp/youtube_dl/extractor/franceinter.py
renalid a942d6cb48
[utils,franceinter] Add french months' names and fix extraction
Update of the "FranceInter" radio extractor : webpages HTML structure
had changed, the extractor didn't work. So I updated this extractor to
get the mp3 URL and all details.
2016-09-14 23:59:38 +07:00

53 lines
1.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
unified_timestamp,
month_by_name,
)
class FranceInterIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
_TEST = {
'url': 'https://www.franceinter.fr/emissions/la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013',
'md5': '4764932e466e6f6c79c317d2e74f6884',
'info_dict': {
'id': 'la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013',
'ext': 'mp3',
'title': 'LHistoire dans les jeux vidéo du 18 décembre 2013 - France Inter',
'description': 'LHistoire dans les jeux vidéo du 18 décembre 2013 par Jean Lebrun en replay sur France Inter. Retrouvez l\'émission en réécoute gratuite et abonnez-vous au podcast !',
'timestamp': 1387324800,
'upload_date': '20131218',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'<button class="replay-button playable" data-is-aod="1" data-url="([^"]+)"', webpage, 'video url')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
extractdate = self._search_regex('(\d{2}-([a-zA-Z\s]+)-\d{4}$)', url, 'extractdate', fatal=False)
extractdate = extractdate.split('-')
extractdate = extractdate[2] + "," + str(month_by_name(extractdate[1], 'fr')) + "," + extractdate[0]
timestamp = unified_timestamp(extractdate)
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'formats': [{
'url': video_url,
'vcodec': 'none',
}],
}