Skip to content

fixed #40 #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
xzycn wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fixed #40 #41

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0f8050b
fixed #40
Mar 21, 2018
81c607c
fixed
Mar 21, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions scrapy_proxies/randomproxy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,14 +36,15 @@ def __init__(self, settings):
self.proxy_list = settings.get('PROXY_LIST')
self.chosen_proxy = ''

proxy_pattern = '(\w+://)([^:]+?:.+@)?(.+)'
if self.mode == Mode.RANDOMIZE_PROXY_EVERY_REQUESTS or self.mode == Mode.RANDOMIZE_PROXY_ONCE:
if self.proxy_list is None:
raise KeyError('PROXY_LIST setting is missing')
self.proxies = {}
fin = open(self.proxy_list)
try:
for line in fin.readlines():
parts = re.match('(\w+://)([^:]+?:[^@]+?@)?(.+)', line.strip())
parts = re.match(proxy_pattern, line.strip())
if not parts:
continue

Expand All @@ -61,7 +62,7 @@ def __init__(self, settings):
elif self.mode == Mode.SET_CUSTOM_PROXY:
custom_proxy = settings.get('CUSTOM_PROXY')
self.proxies = {}
parts = re.match('(\w+://)([^:]+?:[^@]+?@)?(.+)', custom_proxy.strip())
parts = re.match(proxy_pattern, custom_proxy.strip())
if not parts:
raise ValueError('CUSTOM_PROXY is not well formatted')

Expand Down