Compare commits

...

3 Commits

Author SHA1 Message Date
pictuga bf86c1e962 crawler: make AutoUA match http(s) type 2020-04-05 16:07:51 +02:00
pictuga d20f6237bd crawler: replace ContentNegoHandler with AlternateHandler
More basic. Sends the same headers no matter what. Make requests more "replicable".
Also, drop "text/xml" from RSS contenttype, too broad, matches garbage
2020-04-05 16:05:59 +02:00
pictuga 8a4d68d72c crawler: drop 'basic' toggle
Can't even remember the use case
2020-04-05 16:03:06 +02:00
2 changed files with 14 additions and 32 deletions

View File

@ -27,13 +27,14 @@ except NameError:
MIMETYPE = {
'xml': ['text/xml', 'application/xml', 'application/rss+xml', 'application/rdf+xml', 'application/atom+xml', 'application/xhtml+xml'],
'rss': ['application/rss+xml', 'application/rdf+xml', 'application/atom+xml'],
'html': ['text/html', 'application/xhtml+xml', 'application/xml']}
DEFAULT_UA = 'Mozilla/5.0 (X11; Linux x86_64; rv:25.0) Gecko/20100101 Firefox/25.0'
def custom_handler(accept=None, strict=False, delay=None, encoding=None, basic=False):
def custom_handler(follow=None, delay=None, encoding=None):
handlers = []
# as per urllib2 source code, these Handelers are added first
@ -51,14 +52,12 @@ def custom_handler(accept=None, strict=False, delay=None, encoding=None, basic=F
handlers.append(HTTPEquivHandler())
handlers.append(HTTPRefreshHandler())
handlers.append(UAHandler(DEFAULT_UA))
if not basic:
handlers.append(AutoRefererHandler())
handlers.append(EncodingFixHandler(encoding))
if accept:
handlers.append(ContentNegociationHandler(MIMETYPE[accept], strict))
if follow:
handlers.append(AlternateHandler(MIMETYPE[follow]))
handlers.append(CacheHandler(force_min=delay))
@ -198,43 +197,28 @@ class UAHandler(BaseHandler):
class AutoRefererHandler(BaseHandler):
def http_request(self, req):
req.add_unredirected_header('Referer', 'http://%s' % req.host)
req.add_unredirected_header('Referer', '%s://%s' % (req.type, req.host))
return req
https_request = http_request
class ContentNegociationHandler(BaseHandler):
" Handler for content negociation. Also parses <link rel='alternate' type='application/rss+xml' href='...' /> "
class AlternateHandler(BaseHandler):
" Follow <link rel='alternate' type='application/rss+xml' href='...' /> "
def __init__(self, accept=None, strict=False):
self.accept = accept
self.strict = strict
def http_request(self, req):
if self.accept is not None:
if isinstance(self.accept, basestring):
self.accept = (self.accept,)
string = ','.join(self.accept)
if self.strict:
string += ',*/*;q=0.9'
req.add_unredirected_header('Accept', string)
return req
def __init__(self, follow=None):
self.follow = follow or []
def http_response(self, req, resp):
contenttype = resp.info().get('Content-Type', '').split(';')[0]
if 200 <= resp.code < 300 and self.accept is not None and self.strict and contenttype in MIMETYPE['html'] and contenttype not in self.accept:
if 200 <= resp.code < 300 and len(self.follow) and contenttype in MIMETYPE['html'] and contenttype not in self.follow:
# opps, not what we were looking for, let's see if the html page suggests an alternative page of the right types
data = resp.read()
links = lxml.html.fromstring(data[:10000]).findall('.//link[@rel="alternate"]')
for link in links:
if link.get('type', '') in self.accept:
if link.get('type', '') in self.follow:
resp.code = 302
resp.msg = 'Moved Temporarily'
resp.headers['location'] = link.get('href')
@ -246,7 +230,6 @@ class ContentNegociationHandler(BaseHandler):
return resp
https_request = http_request
https_response = http_response

View File

@ -252,7 +252,7 @@ def ItemFill(item, options, feedurl='/', fast=False):
delay = -2
try:
con = crawler.custom_handler('html', False, delay, options.encoding).open(link, timeout=TIMEOUT)
con = crawler.custom_handler(delay=delay, encoding=options.encoding).open(link, timeout=TIMEOUT)
data = con.read()
except (IOError, HTTPException) as e:
@ -335,8 +335,7 @@ def FeedFetch(url, options):
delay = 0
try:
con = crawler.custom_handler(accept='xml', strict=True, delay=delay,
encoding=options.encoding, basic=not options.items) \
con = crawler.custom_handler(follow='rss', delay=delay, encoding=options.encoding) \
.open(url, timeout=TIMEOUT * 2)
xml = con.read()