From bfabd17b33d47f1e973121483623768010880845 Mon Sep 17 00:00:00 2001 From: Genki Sky Date: Tue, 8 Aug 2017 22:49:57 -0400 Subject: [PATCH] Add new extractor --- youtube_dl/extractor/clippit.py | 74 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 75 insertions(+) create mode 100644 youtube_dl/extractor/clippit.py diff --git a/youtube_dl/extractor/clippit.py b/youtube_dl/extractor/clippit.py new file mode 100644 index 000000000..a1a7a774c --- /dev/null +++ b/youtube_dl/extractor/clippit.py @@ -0,0 +1,74 @@ +# coding: utf-8 + +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + qualities, +) + +import re + + +class ClippitIE(InfoExtractor): + + _VALID_URL = r'https?://(?:www\.)?clippituser\.tv/c/(?P[a-z]+)' + _TEST = { + 'url': 'https://www.clippituser.tv/c/evmgm', + 'md5': '963ae7a59a2ec4572ab8bf2f2d2c5f09', + 'info_dict': { + 'id': 'evmgm', + 'ext': 'mp4', + 'title': 'Bye bye Brutus. #BattleBots - Clippit', + 'uploader': 'lizllove', + 'uploader_url': 'https://www.clippituser.tv/p/lizllove', + 'timestamp': 1472183818, + 'upload_date': '20160826', + 'description': 'BattleBots | ABC', + 'thumbnail': r're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'(.+?)', webpage, 'title') + + FORMATS = ('sd', 'hd') + quality = qualities(FORMATS) + formats = [] + for format_id in FORMATS: + url = self._html_search_regex(r'data-%s-file="(.+?)"' % format_id, + webpage, 'url', fatal=False) + if not url: + continue + match = re.search(r'/(?P\d+)\.mp4', url) + formats.append({ + 'url': url, + 'format_id': format_id, + 'quality': quality(format_id), + 'height': int(match.group('height')) if match else None, + }) + + uploader = self._html_search_regex(r'class="username".*>\s+(.+?)\n', + webpage, 'uploader', fatal=False) + uploader_url = ('https://www.clippituser.tv/p/' + uploader + if uploader else None) + + timestamp = self._html_search_regex(r'datetime="(.+?)"', + webpage, 'date', fatal=False) + thumbnail = self._html_search_regex(r'data-image="(.+?)"', + webpage, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'uploader': uploader, + 'uploader_url': uploader_url, + 'timestamp': parse_iso8601(timestamp), + 'description': self._og_search_description(webpage), + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index fb79a1736..ccfa14e7a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -187,6 +187,7 @@ from .chirbit import ( from .cinchcast import CinchcastIE from .cjsw import CJSWIE from .cliphunter import CliphunterIE +from .clippit import ClippitIE from .cliprs import ClipRsIE from .clipsyndicate import ClipsyndicateIE from .closertotruth import CloserToTruthIE