Skip to content
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

Fingerprint update for scrapy 2.7 #7

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+5 −5
Open

Fingerprint update for scrapy 2.7 #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dd4317f
Update middlewares.py
Oct 31, 2022
b6075e5
Update __init__.py
Oct 31, 2022
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
2 changes: 1 addition & 1 deletion scrapy_crawl_once/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
# -*- coding: utf-8 -*-
__version__ = '0.1.1'
__version__ = '0.1.2'
from .middlewares import CrawlOnceMiddleware
8 changes: 4 additions & 4 deletions scrapy_crawl_once/middlewares.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@
from sqlitedict import SqliteDict
from scrapy import signals
from scrapy.utils.project import data_path
from scrapy.utils.request import request_fingerprint
from scrapy.exceptions import IgnoreRequest, NotConfigured

logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -56,10 +55,11 @@ class CrawlOnceMiddleware(object):
them out at Downloader.
"""

def __init__(self, path, stats, default):
def __init__(self, path, stats, default, crawler):
self.path = path
self.stats = stats
self.default = default
self.crawler = crawler

@classmethod
def from_crawler(cls, crawler):
Expand All @@ -69,7 +69,7 @@ def from_crawler(cls, crawler):
path = data_path(s.get('CRAWL_ONCE_PATH', 'crawl_once'),
createdir=True)
default = s.getbool('CRAWL_ONCE_DEFAULT', default=False)
o = cls(path, crawler.stats, default)
o = cls(path, crawler.stats, default, crawler)
crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(o.spider_closed, signal=signals.spider_closed)
return o
Expand All @@ -96,7 +96,7 @@ def _spider_db(self, spider):

def _get_key(self, request):
return (request.meta.get('crawl_once_key') or
request_fingerprint(request))
self.crawler.request_fingerprinter.fingerprint(request))

# spider middleware interface
def process_spider_output(self, response, result, spider):
Expand Down