1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
"""
HttpError Spider Middleware
See documentation in docs/topics/spider-middleware.rst
"""
from scrapy.exceptions import IgnoreRequest
from scrapy import log
class HttpError(IgnoreRequest):
"""A non-200 response was filtered"""
def __init__(self, response, *args, **kwargs):
self.response = response
super(HttpError, self).__init__(*args, **kwargs)
class HttpErrorMiddleware(object):
@classmethod
def from_crawler(cls, crawler):
return cls(crawler.settings)
def __init__(self, settings):
self.handle_httpstatus_all = settings.getbool('HTTPERROR_ALLOW_ALL')
self.handle_httpstatus_list = settings.getlist('HTTPERROR_ALLOWED_CODES')
def process_spider_input(self, response, spider):
if 200 <= response.status < 300: # common case
return
meta = response.meta
if 'handle_httpstatus_all' in meta:
return
if 'handle_httpstatus_list' in meta:
allowed_statuses = meta['handle_httpstatus_list']
elif self.handle_httpstatus_all:
return
else:
allowed_statuses = getattr(spider, 'handle_httpstatus_list', self.handle_httpstatus_list)
if response.status in allowed_statuses:
return
raise HttpError(response, 'Ignoring non-200 response')
def process_spider_exception(self, response, exception, spider):
if isinstance(exception, HttpError):
log.msg(
format="Ignoring response %(response)r: HTTP status code is not handled or not allowed",
level=log.DEBUG,
spider=spider,
response=response
)
return []
|
