From 3764e757a6f9d143842f215e7e96e53bd99f7c77 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Joaqu=C3=ADn=20Rufo=20Gutierrez?= Date: Mon, 1 Oct 2018 17:28:41 +0200 Subject: [PATCH] [fastfiles] Add new extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/fastfiles.py | 42 ++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) create mode 100644 youtube_dl/extractor/fastfiles.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 464c8d690..1c2db635f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -347,6 +347,7 @@ from .facebook import ( FacebookIE, FacebookPluginsVideoIE, ) +from .fastfiles import FastFiles from .faz import FazIE from .fc2 import ( FC2IE, diff --git a/youtube_dl/extractor/fastfiles.py b/youtube_dl/extractor/fastfiles.py new file mode 100644 index 000000000..bfc0a18c7 --- /dev/null +++ b/youtube_dl/extractor/fastfiles.py @@ -0,0 +1,42 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class FastFiles(InfoExtractor): + _VALID_URL = r'https?://(?:fastfiles\.)?bubbleapps\.io/(?P[0-9]+)' + _TEST = { + 'url': 'https://fastfiles-cache1.webcindario.com/48395d.json', + 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', + 'info_dict': { + 'id': 'mp3', + 'ext': 'mp3', + 'title': 'Lucero del Alba - Rondallas de Ferrolterra - 07 - Trova', + 'thumbnail': r're:^https?://.*\.jpg$', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + def _download_json_handle( + self, url_or_request, video_id, note='Downloading JSON metadata', + errnote='Unable to download JSON metadata', transform_source=None, + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + # TODO more code goes here, for example ... + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), + # TODO more properties (see youtube_dl/extractor/common.py) + } \ No newline at end of file