RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

refactor: Use `safe_url_string` to standardize url output

This commit is contained in:
Laerte Pereira 2022-09-06 10:03:18 -03:00
parent 1289422284
commit 582a6bf6db
No known key found for this signature in database
GPG Key ID: BB69B5C731BB8A80
1 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
tests/test_spider.py
View File

@ -22,8 +22,7 @@ from scrapy.spiders import (
from scrapy.linkextractors import LinkExtractor
from scrapy.utils.test import get_crawler
from tests import get_testdata
from pkg_resources import parse_version
from w3lib import __version__ as w3lib_version
from w3lib.url import safe_url_string
class SpiderTest(unittest.TestCase):
@ -362,12 +361,10 @@ class CrawlSpiderTest(SpiderTest):
output = list(spider._requests_to_follow(response))
self.assertEqual(len(output), 3)
self.assertTrue(all(map(lambda r: isinstance(r, Request), output)))
urls = ['http://EXAMPLE.ORG/SOMEPAGE/ITEM/12.HTML',
'http://EXAMPLE.ORG/ABOUT.HTML',
'http://EXAMPLE.ORG/NOFOLLOW.HTML']
if parse_version(w3lib_version) >= parse_version('2.0.0'):
urls = list(map(lambda u: u.replace("EXAMPLE.ORG", "example.org"), urls))
self.assertEqual([r.url for r in output], urls)
self.assertEqual([r.url for r in output],
[safe_url_string('http://EXAMPLE.ORG/SOMEPAGE/ITEM/12.HTML'),
safe_url_string('http://EXAMPLE.ORG/ABOUT.HTML'),
safe_url_string('http://EXAMPLE.ORG/NOFOLLOW.HTML')])
def test_process_request_instance_method_with_response(self):