From faca6745104e197b856137e12e4719032017174c Mon Sep 17 00:00:00 2001 From: trasssh <94064652+trassshhub@users.noreply.github.com> Date: Tue, 11 Jan 2022 00:44:04 +0800 Subject: [PATCH] [Rule34video] Add extractor (#2279) Authored by: trassshhub --- yt_dlp/extractor/extractors.py | 1 + yt_dlp/extractor/rule34video.py | 65 +++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) create mode 100644 yt_dlp/extractor/rule34video.py diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index e63d4b6f5..cc31c7474 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -1301,6 +1301,7 @@ from .rtvnh import RTVNHIE from .rtvs import RTVSIE from .ruhd import RUHDIE +from .rule34video import Rule34VideoIE from .rumble import ( RumbleEmbedIE, RumbleChannelIE, diff --git a/yt_dlp/extractor/rule34video.py b/yt_dlp/extractor/rule34video.py new file mode 100644 index 000000000..522d4ccd5 --- /dev/null +++ b/yt_dlp/extractor/rule34video.py @@ -0,0 +1,65 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re + +from ..utils import parse_duration +from .common import InfoExtractor + + +class Rule34VideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rule34video\.com/videos/(?P\d+)' + _TESTS = [ + { + 'url': 'https://rule34video.com/videos/3065157/shot-it-mmd-hmv/', + 'md5': 'ffccac2c23799dabbd192621ae4d04f3', + 'info_dict': { + 'id': '3065157', + 'ext': 'mp4', + 'title': 'Shot It-(mmd hmv)', + 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065157/preview.jpg', + 'duration': 347.0, + 'age_limit': 18 + } + }, + { + 'url': 'https://rule34video.com/videos/3065296/lara-in-trouble-ep-7-wildeerstudio/', + 'md5': '6bb5169f9f6b38cd70882bf2e64f6b86', + 'info_dict': { + 'id': '3065296', + 'ext': 'mp4', + 'title': 'Lara in Trouble Ep. 7 [WildeerStudio]', + 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065296/preview.jpg', + 'duration': 938.0, + 'age_limit': 18 + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + formats = [] + + for mobj in re.finditer(r']+href="(?P[^"]+download=true[^"]+)".*>(?P[^\s]+) (?P[^<]+)p', webpage): + url, ext, quality = mobj.groups() + formats.append({ + 'url': url, + 'ext': ext.lower(), + 'quality': quality, + }) + + title = self._html_search_regex(r'([^<]+)', webpage, 'title') + thumbnail = self._html_search_regex(r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None) + duration = self._html_search_regex(r'"icon-clock">\s+((?:\d+:?)+)', webpage, 'duration', default=None) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'thumbnail': thumbnail, + 'duration': parse_duration(duration), + 'age_limit': 18 + }