mirror of
https://codeberg.org/polarisfm/youtube-dl
synced 2024-11-23 17:04:33 +01:00
81 lines
3.3 KiB
Python
81 lines
3.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import ExtractorError
|
|
|
|
|
|
class BRIE(InfoExtractor):
|
|
IE_DESC = "Bayerischer Rundfunk Mediathek"
|
|
_VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?P<id>[a-z0-9\-]+)\.html$"
|
|
_BASE_URL = "http://www.br.de"
|
|
|
|
_TEST = {
|
|
"url": "http://www.br.de/mediathek/video/anselm-gruen-114.html",
|
|
"md5": "c4f83cf0f023ba5875aba0bf46860df2",
|
|
"info_dict": {
|
|
"id": "2c8d81c5-6fb7-4a74-88d4-e768e5856532",
|
|
"ext": "mp4",
|
|
"title": "Feiern und Verzichten",
|
|
"description": "Anselm Grün: Feiern und Verzichten",
|
|
"uploader": "BR/Birgit Baier",
|
|
"upload_date": "20140301"
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
display_id = mobj.group('id')
|
|
page = self._download_webpage(url, display_id)
|
|
xml_url = self._search_regex(
|
|
r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL")
|
|
xml = self._download_xml(self._BASE_URL + xml_url, None)
|
|
|
|
videos = [{
|
|
"id": xml_video.get("externalId"),
|
|
"title": xml_video.find("title").text,
|
|
"formats": self._extract_formats(xml_video.find("assets")),
|
|
"thumbnails": self._extract_thumbnails(xml_video.find("teaserImage/variants")),
|
|
"description": " ".join(xml_video.find("shareTitle").text.splitlines()),
|
|
"uploader": xml_video.find("author").text,
|
|
"upload_date": "".join(reversed(xml_video.find("broadcastDate").text.split("."))),
|
|
"webpage_url": xml_video.find("permalink").text,
|
|
} for xml_video in xml.findall("video")]
|
|
|
|
if len(videos) > 1:
|
|
self._downloader.report_warning(
|
|
'found multiple videos; please '
|
|
'report this with the video URL to http://yt-dl.org/bug')
|
|
if not videos:
|
|
raise ExtractorError('No video entries found')
|
|
return videos[0]
|
|
|
|
def _extract_formats(self, assets):
|
|
formats = [{
|
|
"url": asset.find("downloadUrl").text,
|
|
"ext": asset.find("mediaType").text,
|
|
"format_id": asset.get("type"),
|
|
"width": int(asset.find("frameWidth").text),
|
|
"height": int(asset.find("frameHeight").text),
|
|
"tbr": int(asset.find("bitrateVideo").text),
|
|
"abr": int(asset.find("bitrateAudio").text),
|
|
"vcodec": asset.find("codecVideo").text,
|
|
"container": asset.find("mediaType").text,
|
|
"filesize": int(asset.find("size").text),
|
|
} for asset in assets.findall("asset")
|
|
if asset.find("downloadUrl") is not None]
|
|
|
|
self._sort_formats(formats)
|
|
return formats
|
|
|
|
def _extract_thumbnails(self, variants):
|
|
thumbnails = [{
|
|
"url": self._BASE_URL + variant.find("url").text,
|
|
"width": int(variant.find("width").text),
|
|
"height": int(variant.find("height").text),
|
|
} for variant in variants.findall("variant")]
|
|
thumbnails.sort(key=lambda x: x["width"] * x["height"], reverse=True)
|
|
return thumbnails
|