mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-24 02:35:12 +00:00
5c2266df4b
compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
67 lines
2.7 KiB
Python
67 lines
2.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
ExtractorError,
|
|
find_xpath_attr,
|
|
sanitized_Request,
|
|
)
|
|
|
|
|
|
class FlickrIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
|
|
_TEST = {
|
|
'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
|
|
'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b',
|
|
'info_dict': {
|
|
'id': '5645318632',
|
|
'ext': 'mp4',
|
|
"description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.",
|
|
"uploader_id": "forestwander-nature-pictures",
|
|
"title": "Dark Hollow Waterfalls"
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
video_id = mobj.group('id')
|
|
video_uploader_id = mobj.group('uploader_id')
|
|
webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
|
|
req = sanitized_Request(webpage_url)
|
|
req.add_header(
|
|
'User-Agent',
|
|
# it needs a more recent version
|
|
'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)')
|
|
webpage = self._download_webpage(req, video_id)
|
|
|
|
secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret')
|
|
|
|
first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
|
|
first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage')
|
|
|
|
node_id = find_xpath_attr(
|
|
first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id',
|
|
'id').text
|
|
|
|
second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
|
|
second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage')
|
|
|
|
self.report_extraction(video_id)
|
|
|
|
stream = second_xml.find('.//STREAM')
|
|
if stream is None:
|
|
raise ExtractorError('Unable to extract video url')
|
|
video_url = stream.attrib['APP'] + stream.attrib['FULLPATH']
|
|
|
|
return {
|
|
'id': video_id,
|
|
'url': video_url,
|
|
'ext': 'mp4',
|
|
'title': self._og_search_title(webpage),
|
|
'description': self._og_search_description(webpage),
|
|
'thumbnail': self._og_search_thumbnail(webpage),
|
|
'uploader_id': video_uploader_id,
|
|
}
|