From a942d6cb48994c5ff14ccef8773fb086a5544970 Mon Sep 17 00:00:00 2001 From: renalid Date: Fri, 2 Sep 2016 18:31:52 +0200 Subject: [PATCH] [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. --- youtube_dl/extractor/franceinter.py | 38 ++++++++++++++++------------- youtube_dl/utils.py | 13 ++++++++-- 2 files changed, 32 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 2369f868da..6dad8d7122 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -2,20 +2,24 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + unified_timestamp, + month_by_name, +) class FranceInterIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P[^?#]+)' + _TEST = { - 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', + 'url': 'https://www.franceinter.fr/emissions/la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013', 'md5': '4764932e466e6f6c79c317d2e74f6884', 'info_dict': { - 'id': '793962', + 'id': 'la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013', 'ext': 'mp3', - 'title': 'L’Histoire dans les jeux vidéo', - 'description': 'md5:7e93ddb4451e7530022792240a3049c7', - 'timestamp': 1387369800, + 'title': 'L’Histoire dans les jeux vidéo du 18 décembre 2013 - France Inter', + 'description': 'L’Histoire 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', }, } @@ -25,17 +29,17 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) - path = self._search_regex( - r'(.+?)', webpage, 'title') - description = self._html_search_regex( - r'(.*?)', - webpage, 'description', fatal=False) - timestamp = int_or_none(self._search_regex( - r'data-date="(\d+)"', webpage, 'upload date', fatal=False)) + 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, diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index ed199c4ad3..623ced625b 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -91,6 +91,10 @@ def register_socks_protocols(): 'January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December'] +FRENCH_MONTH_NAMES = [ + 'janvier', 'fevrier', 'mars', 'avril', 'mai', 'juin', + 'juillet', 'aout', 'septembre', 'octobre', 'novembre', 'decembre'] + KNOWN_EXTENSIONS = ( 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac', 'flv', 'f4v', 'f4a', 'f4b', @@ -1587,11 +1591,16 @@ def parse_count(s): return lookup_unit_table(_UNIT_TABLE, s) -def month_by_name(name): +def month_by_name(name, lang='en'): """ Return the number of a month by (locale-independently) English name """ + name_list = ENGLISH_MONTH_NAMES + + if lang == 'fr': + name_list = FRENCH_MONTH_NAMES + try: - return ENGLISH_MONTH_NAMES.index(name) + 1 + return name_list.index(name) + 1 except ValueError: return None