You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
144 lines
4.9 KiB
Python
144 lines
4.9 KiB
Python
# Define here the models for your spider middleware
|
|
#
|
|
# See documentation in:
|
|
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
import logging
|
|
from typing import Optional
|
|
from scrapy import signals
|
|
|
|
# useful for handling different item types with a single interface
|
|
from itemadapter import ItemAdapter
|
|
from scrapy.http.headers import Headers
|
|
|
|
from science_article_cssci.scripts.get_cookie import GetSessionID
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class ScienceArticleCssciSpiderMiddleware:
|
|
# Not all methods need to be defined. If a method is not defined,
|
|
# scrapy acts as if the spider middleware does not modify the
|
|
# passed objects.
|
|
|
|
@classmethod
|
|
def from_crawler(cls, crawler):
|
|
# This method is used by Scrapy to create your spiders.
|
|
s = cls()
|
|
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
return s
|
|
|
|
def process_spider_input(self, response, spider):
|
|
# Called for each response that goes through the spider
|
|
# middleware and into the spider.
|
|
|
|
# Should return None or raise an exception.
|
|
return None
|
|
|
|
def process_spider_output(self, response, result, spider):
|
|
# Called with the results returned from the Spider, after
|
|
# it has processed the response.
|
|
|
|
# Must return an iterable of Request, or item objects.
|
|
for i in result:
|
|
yield i
|
|
|
|
def process_spider_exception(self, response, exception, spider):
|
|
# Called when a spider or process_spider_input() method
|
|
# (from other spider middleware) raises an exception.
|
|
|
|
# Should return either None or an iterable of Request or item objects.
|
|
pass
|
|
|
|
async def process_start(self, start):
|
|
# Called with an async iterator over the spider start() method or the
|
|
# maching method of an earlier spider middleware.
|
|
async for item_or_request in start:
|
|
yield item_or_request
|
|
|
|
def spider_opened(self, spider):
|
|
spider.logger.info("Spider opened: %s" % spider.name)
|
|
|
|
|
|
class ScienceArticleCssciDownloaderMiddleware:
|
|
# Not all methods need to be defined. If a method is not defined,
|
|
# scrapy acts as if the downloader middleware does not modify the
|
|
# passed objects.
|
|
|
|
@classmethod
|
|
def from_crawler(cls, crawler):
|
|
# This method is used by Scrapy to create your spiders.
|
|
s = cls()
|
|
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
return s
|
|
|
|
def process_request(self, request, spider):
|
|
# Called for each request that goes through the downloader
|
|
# middleware.
|
|
|
|
# Must either:
|
|
# - return None: continue processing this request
|
|
# - or return a Response object
|
|
# - or return a Request object
|
|
# - or raise IgnoreRequest: process_exception() methods of
|
|
# installed downloader middleware will be called
|
|
return None
|
|
|
|
def process_response(self, request, response, spider):
|
|
# Called with the response returned from the downloader.
|
|
|
|
# Must either;
|
|
# - return a Response object
|
|
# - return a Request object
|
|
# - or raise IgnoreRequest
|
|
return response
|
|
|
|
def process_exception(self, request, exception, spider):
|
|
# Called when a download handler or a process_request()
|
|
# (from other downloader middleware) raises an exception.
|
|
|
|
# Must either:
|
|
# - return None: continue processing this exception
|
|
# - return a Response object: stops process_exception() chain
|
|
# - return a Request object: stops process_exception() chain
|
|
pass
|
|
|
|
def spider_opened(self, spider):
|
|
spider.logger.info("Spider opened: %s" % spider.name)
|
|
|
|
|
|
class CssciCookieMiddleware:
|
|
ss: Optional[GetSessionID]
|
|
|
|
def __init__(self, custom_headers: dict, cookie_cfg: dict):
|
|
self.custom_headers = custom_headers
|
|
self.headers = Headers(self.custom_headers)
|
|
self.cookies_pool_config = cookie_cfg
|
|
|
|
@classmethod
|
|
def from_crawler(cls, crawler):
|
|
settings = crawler.settings
|
|
post_headers = crawler.settings.getdict('POST_HEADERS_CONFIG')
|
|
s = cls(
|
|
custom_headers=post_headers,
|
|
cookie_cfg=dict(
|
|
redis_uri=settings.get("COOKIE_POOL_CONFIG"),
|
|
pool_key=settings.get("COOKIE_POOL_REDIS_KEY"),
|
|
ttl=settings.get("COOKIE_REDIS_TTL")
|
|
)
|
|
)
|
|
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
return s
|
|
|
|
def spider_opened(self, spider):
|
|
self.ss = GetSessionID(**self.cookies_pool_config)
|
|
|
|
async def process_request(self, request, spider):
|
|
cookie_1 = await self.ss.get_cookie_from_redis()
|
|
if not cookie_1:
|
|
cookie_1 = await self.ss.get_cookie_to_redis()
|
|
logger.info("""
|
|
没有可用cookie
|
|
重新获取: %s""" % cookie_1)
|
|
|
|
request.cookies = cookie_1
|
|
request.headers = self.headers
|