Move custom_handler to crawler

Makes more sense. Easier to reuse. Also cleaned up a bit the code
master
pictuga 2017-03-18 22:51:27 -10:00
parent beec6469cc
commit 2003e2760b
2 changed files with 24 additions and 17 deletions

View File

@ -29,6 +29,28 @@ MIMETYPE = {
'xml': ['text/xml', 'application/xml', '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):
handlers = []
handlers.append(GZIPHandler())
handlers.append(HTTPEquivHandler())
handlers.append(HTTPRefreshHandler())
if not basic:
handlers.append(UAHandler(DEFAULT_UA))
handlers.append(AutoRefererHandler())
handlers.append(EncodingFixHandler(encoding))
handlers.append(ContentNegociationHandler(MIMETYPE[accept], strict))
handlers.append(SQliteCacheHandler(delay))
return build_opener(*handlers)
class GZIPHandler(BaseHandler):
def http_request(self, req):
req.add_unredirected_header('Accept-Encoding', 'gzip')

View File

@ -48,8 +48,6 @@ THREADS = 10 # number of threads (1 for single-threaded)
DEBUG = False
PORT = 8080
DEFAULT_UA = 'Mozilla/5.0 (X11; Linux x86_64; rv:25.0) Gecko/20100101 Firefox/25.0'
PROTOCOL = ['http', 'https', 'ftp']
@ -127,19 +125,6 @@ def parseOptions(options):
return out
default_handlers = [crawler.GZIPHandler(), crawler.UAHandler(DEFAULT_UA),
crawler.AutoRefererHandler(), crawler.HTTPEquivHandler(),
crawler.HTTPRefreshHandler()]
def custom_handler(accept, strict=False, delay=DELAY, encoding=None):
handlers = default_handlers[:]
handlers.append(crawler.EncodingFixHandler(encoding))
handlers.append(crawler.ContentNegociationHandler(crawler.MIMETYPE[accept], strict))
handlers.append(crawler.SQliteCacheHandler(delay))
return build_opener(*handlers)
def ItemFix(item, feedurl='/'):
""" Improves feed items (absolute links, resolve feedburner links, etc) """
@ -267,7 +252,7 @@ def ItemFill(item, options, feedurl='/', fast=False):
delay = -2
try:
con = custom_handler('html', False, delay, options.encoding).open(link, timeout=TIMEOUT)
con = crawler.custom_handler('html', False, delay, options.encoding).open(link, timeout=TIMEOUT)
data = con.read()
except (IOError, HTTPException) as e:
@ -368,7 +353,7 @@ def FeedFetch(url, options):
delay = 0
try:
con = custom_handler('xml', True, delay, options.encoding).open(url, timeout=TIMEOUT * 2)
con = crawler.custom_handler('xml', True, delay, options.encoding).open(url, timeout=TIMEOUT * 2)
xml = con.read()
except (HTTPError) as e: