File: downloadtimeout.py

package info (click to toggle)
python-scrapy 2.4.1-2%2Bdeb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 4,748 kB
  • sloc: python: 32,888; xml: 199; makefile: 90; sh: 7
file content (26 lines) | stat: -rw-r--r-- 701 bytes parent folder | download
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
"""
Download timeout middleware

See documentation in docs/topics/downloader-middleware.rst
"""

from scrapy import signals


class DownloadTimeoutMiddleware:

    def __init__(self, timeout=180):
        self._timeout = timeout

    @classmethod
    def from_crawler(cls, crawler):
        o = cls(crawler.settings.getfloat('DOWNLOAD_TIMEOUT'))
        crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
        return o

    def spider_opened(self, spider):
        self._timeout = getattr(spider, 'download_timeout', self._timeout)

    def process_request(self, request, spider):
        if self._timeout:
            request.meta.setdefault('download_timeout', self._timeout)