Ausgabe der neuen DB Einträge

This commit is contained in:
hubobel 2022-01-02 21:50:48 +01:00
parent bad48e1627
commit cfbbb9ee3d
2399 changed files with 843193 additions and 43 deletions

View file

@ -0,0 +1,23 @@
"""Set User-Agent header per spider or use a default value from settings"""
from scrapy import signals
class UserAgentMiddleware:
"""This middleware allows spiders to override the user_agent"""
def __init__(self, user_agent='Scrapy'):
self.user_agent = user_agent
@classmethod
def from_crawler(cls, crawler):
o = cls(crawler.settings['USER_AGENT'])
crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
return o
def spider_opened(self, spider):
self.user_agent = getattr(spider, 'user_agent', self.user_agent)
def process_request(self, request, spider):
if self.user_agent:
request.headers.setdefault(b'User-Agent', self.user_agent)