mirror of
https://github.com/crawlab-team/crawlab.git
synced 2026-01-22 17:31:03 +01:00
Update spider.py
修复“//” 开头的url报错 ValueError('Missing scheme in request url: %s' % self._url)
This commit is contained in:
@@ -9,7 +9,7 @@ def get_real_url(response, url):
|
||||
return url
|
||||
elif re.search(r'^\/\/', url):
|
||||
u = urlparse(response.url)
|
||||
return u.scheme + url
|
||||
return u.scheme + ":" + url
|
||||
return urljoin(response.url, url)
|
||||
|
||||
class ConfigSpider(scrapy.Spider):
|
||||
|
||||
Reference in New Issue
Block a user