From 4dc19c0982e4190a88a18b92afd940d6866a2c04 Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Tue, 30 Sep 2014 02:26:16 +0300 Subject: [PATCH] [lrt] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/lrt.py | 69 ++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) create mode 100644 youtube_dl/extractor/lrt.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 89a9d8106..ce1a2b32b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -190,6 +190,7 @@ LivestreamOriginalIE, LivestreamShortenerIE, ) +from .lrt import LRTIE from .lynda import ( LyndaIE, LyndaCourseIE diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py new file mode 100644 index 000000000..fca0bfef0 --- /dev/null +++ b/youtube_dl/extractor/lrt.py @@ -0,0 +1,69 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + js_to_json, + parse_duration, + remove_end, +) + + +class LRTIE(InfoExtractor): + IE_NAME = 'lrt.lt' + _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.lrt.lt/mediateka/irasas/54391/', + 'info_dict': { + 'id': '54391', + 'ext': 'mp4', + 'title': 'Septynios Kauno dienos', + 'description': 'Kauno miesto ir apskrities naujienos', + 'duration': 1783, + }, + 'params': { + 'skip_download': True, # HLS download + }, + + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + title = remove_end(self._og_search_title(webpage), ' - LRT') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + duration = parse_duration(self._search_regex( + r"'duration':\s*'([^']+)',", webpage, + 'duration', fatal=False, default=None)) + + formats = [] + for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage): + data = json.loads(js_to_json(js)) + if data['provider'] == 'rtmp': + formats.append({ + 'format_id': 'rtmp', + 'ext': determine_ext(data['file']), + 'url': data['streamer'], + 'play_path': 'mp4:%s' % data['file'], + 'preference': -1, + }) + else: + formats.extend( + self._extract_m3u8_formats(data['file'], video_id, 'mp4')) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + }