[br] Simplify
Philipp Hagemeister
10 years ago
parent
1052d2bfec
commit
06aabfc422
@ -1,82 +1,79 @@
|
|||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
|
||||||
class BRIE(InfoExtractor):
|
|
||||||
|
|
||||||
IE_DESC = u"Bayerischer Rundfunk Mediathek"
|
class BRIE(InfoExtractor):
|
||||||
_VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?:[a-z0-9\-]+\.html)$"
|
IE_DESC = "Bayerischer Rundfunk Mediathek"
|
||||||
_BASE_URL = u"http://www.br.de"
|
_VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?P<id>[a-z0-9\-]+)\.html$"
|
||||||
|
_BASE_URL = "http://www.br.de"
|
||||||
|
|
||||||
_TESTS = [
|
_TEST = {
|
||||||
{
|
"url": "http://www.br.de/mediathek/video/anselm-gruen-114.html",
|
||||||
u"url": u"http://www.br.de/mediathek/video/anselm-gruen-114.html",
|
"md5": "c4f83cf0f023ba5875aba0bf46860df2",
|
||||||
u"file": u"2c8d81c5-6fb7-4a74-88d4-e768e5856532.mp4",
|
"info_dict": {
|
||||||
u"md5": u"c4f83cf0f023ba5875aba0bf46860df2",
|
"id": "2c8d81c5-6fb7-4a74-88d4-e768e5856532",
|
||||||
u"info_dict": {
|
"ext": "mp4",
|
||||||
u"title": u"Feiern und Verzichten",
|
"title": "Feiern und Verzichten",
|
||||||
u"description": u"Anselm Grün: Feiern und Verzichten",
|
"description": "Anselm Grün: Feiern und Verzichten",
|
||||||
u"uploader": u"BR/Birgit Baier",
|
"uploader": "BR/Birgit Baier",
|
||||||
u"upload_date": u"20140301"
|
"upload_date": "20140301"
|
||||||
}
|
|
||||||
}
|
}
|
||||||
]
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
page = self._download_webpage(url, None)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
xml_url = self._search_regex(r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL")
|
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)
|
xml = self._download_xml(self._BASE_URL + xml_url, None)
|
||||||
|
|
||||||
videos = []
|
videos = [{
|
||||||
for xml_video in xml.findall("video"):
|
"id": xml_video.get("externalId"),
|
||||||
video = {}
|
"title": xml_video.find("title").text,
|
||||||
video["id"] = xml_video.get("externalId")
|
"formats": self._extract_formats(xml_video.find("assets")),
|
||||||
video["title"] = xml_video.find("title").text
|
"thumbnails": self._extract_thumbnails(xml_video.find("teaserImage/variants")),
|
||||||
video["formats"] = self._extract_formats(xml_video.find("assets"))
|
"description": " ".join(xml_video.find("shareTitle").text.splitlines()),
|
||||||
video["thumbnails"] = self._extract_thumbnails(xml_video.find("teaserImage/variants"))
|
"uploader": xml_video.find("author").text,
|
||||||
video["thumbnail"] = video["thumbnails"][0]["url"]
|
"upload_date": "".join(reversed(xml_video.find("broadcastDate").text.split("."))),
|
||||||
video["description"] = " ".join(xml_video.find("shareTitle").text.splitlines())
|
"webpage_url": xml_video.find("permalink").text,
|
||||||
video["uploader"] = xml_video.find("author").text
|
} for xml_video in xml.findall("video")]
|
||||||
video["upload_date"] = "".join(reversed(xml_video.find("broadcastDate").text.split(".")))
|
|
||||||
video["webpage_url"] = xml_video.find("permalink").text
|
|
||||||
videos.append(video)
|
|
||||||
|
|
||||||
if len(videos) > 1:
|
if len(videos) > 1:
|
||||||
self._downloader.report_warning(u'found multiple videos; please'
|
self._downloader.report_warning(
|
||||||
u'report this with the video URL to http://yt-dl.org/bug')
|
'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]
|
return videos[0]
|
||||||
|
|
||||||
def _extract_formats(self, assets):
|
def _extract_formats(self, assets):
|
||||||
vformats = []
|
formats = [{
|
||||||
for asset in assets.findall("asset"):
|
"url": asset.find("downloadUrl").text,
|
||||||
if asset.find("downloadUrl") is None:
|
"ext": asset.find("mediaType").text,
|
||||||
continue
|
"format_id": asset.get("type"),
|
||||||
vformat = {}
|
"width": int(asset.find("frameWidth").text),
|
||||||
vformat["url"] = asset.find("downloadUrl").text
|
"height": int(asset.find("frameHeight").text),
|
||||||
vformat["ext"] = asset.find("mediaType").text
|
"tbr": int(asset.find("bitrateVideo").text),
|
||||||
vformat["format_id"] = asset.get("type")
|
"abr": int(asset.find("bitrateAudio").text),
|
||||||
vformat["width"] = int(asset.find("frameWidth").text)
|
"vcodec": asset.find("codecVideo").text,
|
||||||
vformat["height"] = int(asset.find("frameHeight").text)
|
"container": asset.find("mediaType").text,
|
||||||
vformat["resolution"] = "%ix%i" % (vformat["width"], vformat["height"])
|
"filesize": int(asset.find("size").text),
|
||||||
vformat["tbr"] = int(asset.find("bitrateVideo").text)
|
} for asset in assets.findall("asset")
|
||||||
vformat["abr"] = int(asset.find("bitrateAudio").text)
|
if asset.find("downloadUrl") is not None]
|
||||||
vformat["vcodec"] = asset.find("codecVideo").text
|
|
||||||
vformat["container"] = vformat["ext"]
|
self._sort_formats(formats)
|
||||||
vformat["filesize"] = int(asset.find("size").text)
|
return formats
|
||||||
vformat["preference"] = vformat["quality"] = -1
|
|
||||||
vformat["format"] = "%s container with %i Kbps %s" % (vformat["container"], vformat["tbr"], vformat["vcodec"])
|
|
||||||
vformats.append(vformat)
|
|
||||||
self._sort_formats(vformats)
|
|
||||||
return vformats
|
|
||||||
|
|
||||||
def _extract_thumbnails(self, variants):
|
def _extract_thumbnails(self, variants):
|
||||||
thumbnails = []
|
thumbnails = [{
|
||||||
for variant in variants.findall("variant"):
|
"url": self._BASE_URL + variant.find("url").text,
|
||||||
thumbnail = {}
|
"width": int(variant.find("width").text),
|
||||||
thumbnail["url"] = self._BASE_URL + variant.find("url").text
|
"height": int(variant.find("height").text),
|
||||||
thumbnail["width"] = int(variant.find("width").text)
|
} for variant in variants.findall("variant")]
|
||||||
thumbnail["height"] = int(variant.find("height").text)
|
thumbnails.sort(key=lambda x: x["width"] * x["height"], reverse=True)
|
||||||
thumbnail["resolution"] = "%ix%i" % (thumbnail["width"], thumbnail["height"])
|
|
||||||
thumbnails.append(thumbnail)
|
|
||||||
thumbnails.sort(key = lambda x: x["width"] * x["height"], reverse=True)
|
|
||||||
return thumbnails
|
return thumbnails
|
||||||
|
|||||||
Loading…
Reference in New Issue