-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-from __future__ import absolute_import
-
import base64
import datetime
import itertools
from .extractor.ard import ARDIE
from .extractor.arte import ArteTvIE
from .extractor.dailymotion import DailymotionIE
+from .extractor.gametrailers import GametrailersIE
+from .extractor.generic import GenericIE
from .extractor.metacafe import MetacafeIE
from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE
-class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
-
- _VALID_URL = r'.*'
- IE_NAME = u'generic'
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- if not self._downloader.params.get('test', False):
- self._downloader.report_warning(u'Falling back on generic information extractor.')
- super(GenericIE, self).report_download_webpage(video_id)
-
- def report_following_redirect(self, new_url):
- """Report information extraction."""
- self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
-
- def _test_redirect(self, url):
- """Check if it is a redirect, like url shorteners, in case return the new url."""
- class HeadRequest(compat_urllib_request.Request):
- def get_method(self):
- return "HEAD"
-
- class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
- """
- Subclass the HTTPRedirectHandler to make it use our
- HeadRequest also on the redirected URL
- """
- def redirect_request(self, req, fp, code, msg, headers, newurl):
- if code in (301, 302, 303, 307):
- newurl = newurl.replace(' ', '%20')
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True)
- else:
- raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
- class HTTPMethodFallback(compat_urllib_request.BaseHandler):
- """
- Fallback to GET if HEAD is not allowed (405 HTTP error)
- """
- def http_error_405(self, req, fp, code, msg, headers):
- fp.read()
- fp.close()
-
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True))
-
- # Build our opener
- opener = compat_urllib_request.OpenerDirector()
- for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
- HTTPMethodFallback, HEADRedirectHandler,
- compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
- opener.add_handler(handler())
-
- response = opener.open(HeadRequest(url))
- if response is None:
- raise ExtractorError(u'Invalid URL protocol')
- new_url = response.geturl()
-
- if url == new_url:
- return False
-
- self.report_following_redirect(new_url)
- return new_url
-
- def _real_extract(self, url):
- new_url = self._test_redirect(url)
- if new_url: return [self.url_result(new_url)]
-
- video_id = url.split('/')[-1]
- try:
- webpage = self._download_webpage(url, video_id)
- except ValueError as err:
- # since this is the last-resort InfoExtractor, if
- # this error is thrown, it'll be thrown here
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- self.report_extraction(video_id)
- # Start with something easy: JW Player in SWFObject
- mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit
- mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit: JWPlayer JS loader
- mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
- if mobj is None:
- # Try to find twitter cards info
- mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
- if mobj is None:
- # We look for Open Graph info:
- # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
- m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
- # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
- if m_video_type is not None:
- mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- # It's possible that one of the regexes
- # matched, but returned an empty group:
- if mobj.group(1) is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- video_url = compat_urllib_parse.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
-
- # here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
-
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- video_title = self._html_search_regex(r'<title>(.*)</title>',
- webpage, u'video title')
-
- # video uploader is domain name
- video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
- url, u'video uploader')
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension,
- }]
-
-
-
-class GoogleSearchIE(SearchInfoExtractor):
- """Information Extractor for Google Video search queries."""
- _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
- _MAX_RESULTS = 1000
- IE_NAME = u'video.google:search'
- _SEARCH_KEY = 'gvsearch'
-
- def _get_n_results(self, query, n):
- """Get a specified number of results for a query"""
-
- res = {
- '_type': 'playlist',
- 'id': query,
- 'entries': []
- }
- for pagenum in itertools.count(1):
- result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
- webpage = self._download_webpage(result_url, u'gvsearch:' + query,
- note='Downloading result page ' + str(pagenum))
- for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
- e = {
- '_type': 'url',
- 'url': mobj.group(1)
- }
- res['entries'].append(e)
- if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
- return res
class YahooSearchIE(SearchInfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
'thumbnail': thumbnail_url,
}]
-class GametrailersIE(InfoExtractor):
- _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
-
- def _real_extract(self, 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_type = mobj.group('type')
- webpage = self._download_webpage(url, video_id)
- if video_type == 'full-episodes':
- mgid_re = r'data-video="(?P<mgid>mgid:.*?)"'
- else:
- mgid_re = r'data-contentId=\'(?P<mgid>mgid:.*?)\''
- mgid = self._search_regex(mgid_re, webpage, u'mgid')
- data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'})
-
- info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data,
- video_id, u'Downloading video info')
- links_webpage = self._download_webpage('http://www.gametrailers.com/feeds/mediagen/?' + data,
- video_id, u'Downloading video urls info')
-
- self.report_extraction(video_id)
- info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
- <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
- <image>.*
- <url>(?P<thumb>.*?)</url>.*
- </image>'''
-
- m_info = re.search(info_re, info_page, re.VERBOSE|re.DOTALL)
- if m_info is None:
- raise ExtractorError(u'Unable to extract video info')
- video_title = m_info.group('title')
- video_description = m_info.group('description')
- video_thumb = m_info.group('thumb')
-
- m_urls = list(re.finditer(r'<src>(?P<url>.*)</src>', links_webpage))
- if m_urls is None or len(m_urls) == 0:
- raise ExtractError(u'Unable to extrat video url')
- # They are sorted from worst to best quality
- video_url = m_urls[-1].group('url')
-
- return {'url': video_url,
- 'id': video_id,
- 'title': video_title,
- # Videos are actually flv not mp4
- 'ext': 'flv',
- 'thumbnail': video_thumb,
- 'description': video_description,
- }
def gen_extractors():
""" Return a list of an instance of every supported extractor.
projects / youtube-dl / blobdiff