From 85a802969ebb62ff57347110f7ad0d87099e65e7 Mon Sep 17 00:00:00 2001 From: milkknife <111794344+milkknife@users.noreply.github.com> Date: Thu, 8 Dec 2022 17:56:36 +0100 Subject: [PATCH] [extractor/webcamerapl] Add extractor (#5715) Authored by: milkknife --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/webcamerapl.py | 44 +++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) create mode 100644 yt_dlp/extractor/webcamerapl.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index b1d0a9fb02..c3eb2bb779 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -2194,6 +2194,7 @@ from .wdr import ( WDRElefantIE, WDRMobileIE, ) +from .webcamerapl import WebcameraplIE from .webcaster import ( WebcasterIE, WebcasterFeedIE, diff --git a/yt_dlp/extractor/webcamerapl.py b/yt_dlp/extractor/webcamerapl.py new file mode 100644 index 0000000000..a02d9519c6 --- /dev/null +++ b/yt_dlp/extractor/webcamerapl.py @@ -0,0 +1,44 @@ +import codecs + +from .common import InfoExtractor + + +class WebcameraplIE(InfoExtractor): + _VALID_URL = r'https?://(?P[\w-]+)\.webcamera\.pl' + _TESTS = [{ + 'url': 'https://warszawa-plac-zamkowy.webcamera.pl', + 'info_dict': { + 'id': 'warszawa-plac-zamkowy', + 'ext': 'mp4', + 'title': r're:WIDOK NA PLAC ZAMKOWY W WARSZAWIE \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', + 'live_status': 'is_live', + } + }, { + 'url': 'https://gdansk-stare-miasto.webcamera.pl/', + 'info_dict': { + 'id': 'gdansk-stare-miasto', + 'ext': 'mp4', + 'title': r're:GDAƃSK - widok na Stare Miasto \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', + 'live_status': 'is_live', + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + rot13_m3u8_url = self._search_regex(r'data-src\s*=\s*"(uggc[^"]+\.z3h8)"', + webpage, 'm3u8 url', default=None) + if not rot13_m3u8_url: + self.raise_no_formats('No video/audio found at the provided url', expected=True) + + m3u8_url = codecs.decode(rot13_m3u8_url, 'rot-13') + formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, live=True) + + return { + 'id': video_id, + 'title': self._html_search_regex(r']*>([^>]+)', webpage, 'title'), + 'formats': formats, + 'subtitles': subtitles, + 'is_live': True, + }