github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[photobucket] Modernize and remove the old extraction code

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-03-09 19:36:46 +01:00
parent ee95c09333
commit 90f3476180
1 changed files with 18 additions and 51 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

69
youtube_dl/extractor/photobucket.py
View file

@ -1,76 +1,43 @@
from __future__ import unicode_literals
import datetime import datetime
import json import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class PhotobucketIE(InfoExtractor): class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com.""" _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
# TODO: the original _VALID_URL was:
# r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
# Check if it's necessary to keep the old extracion process
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
IE_NAME = u'photobucket'
_TEST = { _TEST = {
u'url': u'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0', u'url': u'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
u'file': u'zpsc0c3b9fa.mp4', u'file': u'zpsc0c3b9fa.mp4',
u'md5': u'7dabfb92b0a31f6c16cebc0f8e60ff99', u'md5': u'7dabfb92b0a31f6c16cebc0f8e60ff99',
u'info_dict': { u'info_dict': {
u"upload_date": u"20130504", 'upload_date': '20130504',
u"uploader": u"rachaneronas", 'uploader': 'rachaneronas',
u"title": u"Tired of Link Building? Try BacklinkMyDomain.com!" 'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id') video_id = mobj.group('id')
video_extension = mobj.group('ext') video_extension = mobj.group('ext')
# Retrieve video webpage to extract further information
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# Extract URL, uploader, and title from webpage # Extract URL, uploader, and title from webpage
self.report_extraction(video_id) self.report_extraction(video_id)
# We try first by looking the javascript code: info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage) webpage, 'info json')
if mobj is not None: info = json.loads(info_json)
info = json.loads(mobj.group('json')) return {
return [{ 'id': video_id,
'id': video_id, 'url': info[u'downloadUrl'],
'url': info[u'downloadUrl'], 'uploader': info[u'username'],
'uploader': info[u'username'], 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'), 'title': info[u'title'],
'title': info[u'title'], 'ext': video_extension,
'ext': video_extension, 'thumbnail': info[u'thumbUrl'],
'thumbnail': info[u'thumbUrl'], }
}]
# We try looking in other parts of the webpage
video_url = self._search_regex(r'<link rel="video_src" href=".*\?file=([^"]+)" />',
webpage, u'video URL')
mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1).decode('utf-8')
video_uploader = mobj.group(2).decode('utf-8')
return [{
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
}]