Move GenericIE into its own file
This commit is contained in:
Philipp Hagemeister
parent
9f4e6bbaeb
commit
9b122384e9
2 changed files with 152 additions and 139 deletions
|
|
@ -27,6 +27,7 @@ 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
|
||||
|
|
@ -45,145 +46,6 @@ from .extractor.zdf import ZDFIE
|
|||
|
||||
|
||||
|
||||
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,
|
||||
}]
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
151
youtube_dl/extractor/generic.py
Normal file
151
youtube_dl/extractor/generic.py
Normal file
|
|
@ -0,0 +1,151 @@
|
|||
import os
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urllib_error,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
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:
|
||||
# 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,
|
||||
}]
|
||||
Loading…
Reference in a new issue