|
|
# Define here the models for your spider middleware
|
|
|
#
|
|
|
# See documentation in:
|
|
|
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
|
from __future__ import annotations
|
|
|
import json
|
|
|
from typing import TYPE_CHECKING
|
|
|
import redis
|
|
|
|
|
|
from scrapy import signals, Spider
|
|
|
from scrapy.exceptions import CloseSpider
|
|
|
# useful for handling different item types with a single interface
|
|
|
from itemadapter import ItemAdapter
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
|
from scrapy.crawler import Crawler
|
|
|
from scrapy import Request
|
|
|
|
|
|
|
|
|
class ScienceArticleWosSpiderMiddleware:
|
|
|
# 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 ScienceArticleWosDownloaderMiddleware:
|
|
|
# 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 WosStarterApiXkeyDownloaderMiddleware:
|
|
|
async def process_request(self, request, spider):
|
|
|
key_param = {
|
|
|
'X-ApiKey': '53b8164e7543ccebe489988287e8b871bc2c0880'
|
|
|
}
|
|
|
request.headers.update(key_param)
|
|
|
# return request
|
|
|
|
|
|
|
|
|
class WosCookieMiddleware:
|
|
|
def __init__(self, redis_uri: str):
|
|
|
self.redis_cli = redis.from_url(redis_uri, decode_responses=True)
|
|
|
self.redis_key_prefix = 'cookie_pool:wos_sid'
|
|
|
self.cookiepool_cache_key = 'cookie_pool:wos:sid_q'
|
|
|
|
|
|
@classmethod
|
|
|
def from_crawler(cls, crawler: Crawler, *args, **kwargs):
|
|
|
settings = crawler.settings
|
|
|
middle = cls(
|
|
|
redis_uri=settings.get("REDIS_URL")
|
|
|
)
|
|
|
crawler.signals.connect(middle.open_spider, signal=signals.spider_opened)
|
|
|
crawler.signals.connect(middle.close_spider, signal=signals.spider_closed)
|
|
|
return middle
|
|
|
|
|
|
def open_spider(self, spider: Spider):
|
|
|
self.loading_sid_from_redis()
|
|
|
|
|
|
def close_spider(self, spider: Spider, reason: str = None):
|
|
|
self.del_sid_from_redis()
|
|
|
|
|
|
def process_request(self, request: Request, spider):
|
|
|
req_wos_sid = request.meta.get('wos_sid')
|
|
|
if not req_wos_sid:
|
|
|
sid = self.get_sid_from_redis()
|
|
|
if not sid:
|
|
|
raise CloseSpider(f"没有获取到sid，即将退出")
|
|
|
# 把获取到的wos_sid绑定到request，可以在parse方法中获取到wos_sid的值
|
|
|
request.meta['wos_sid'] = sid
|
|
|
else:
|
|
|
sid = req_wos_sid
|
|
|
|
|
|
cookie_1 = {'dotmatics.elementalKey': 'SLsLWlMhrHnTjDerSrlG'}
|
|
|
|
|
|
headers = {
|
|
|
'authority': 'webofscience.clarivate.cn',
|
|
|
'accept-language': 'zh-CN,zh;q=0.9',
|
|
|
'cache-control': 'no-cache',
|
|
|
'origin': 'https://webofscience.clarivate.cn',
|
|
|
'pragma': 'no-cache',
|
|
|
# 'referer': 'https://webofscience.clarivate.cn/wos/woscc/advanced-search',
|
|
|
}
|
|
|
request.cookies = cookie_1
|
|
|
|
|
|
if request.url.endswith('runQuerySearch'):
|
|
|
# 检索时需要带有sid参数
|
|
|
request._set_url(request.url + "?SID=%s" % sid)
|
|
|
headers.update(
|
|
|
{'accept': 'application/x-ndjson', 'content-type': 'text/plain;charset=UTF-8'})
|
|
|
else:
|
|
|
headers.update(
|
|
|
{'accept': 'application/json, text/plain, */*', 'content-type': 'application/json',
|
|
|
'x-1p-wos-sid': sid})
|
|
|
for hk, hv in headers.items():
|
|
|
request.headers[hk] = hv
|
|
|
|
|
|
return None
|
|
|
|
|
|
def process_response(self, request, response, spider):
|
|
|
if response.status != 200:
|
|
|
self.mark_sid_status(request.meta.get('wos_sid'))
|
|
|
|
|
|
return response
|
|
|
|
|
|
def get_sid_from_redis(self):
|
|
|
val = self.redis_cli.rpoplpush(self.cookiepool_cache_key, self.cookiepool_cache_key)
|
|
|
if val:
|
|
|
self.redis_cli.hincrby(f'{self.redis_key_prefix}:{val}', 'used_times', 1)
|
|
|
return val
|
|
|
return None
|
|
|
|
|
|
def mark_sid_status(self, sid: str, status: str = 'validate'):
|
|
|
"""
|
|
|
:param sid:
|
|
|
:param status: validate/expired
|
|
|
:return:
|
|
|
"""
|
|
|
if status == "expired":
|
|
|
# 过期直接删除key
|
|
|
self.redis_cli.delete(f'{self.cookiepool_cache_key}:{sid}')
|
|
|
else:
|
|
|
self.redis_cli.hset(f'{self.redis_key_prefix}:{sid}', 'status', status)
|
|
|
|
|
|
def loading_sid_from_redis(self) -> list:
|
|
|
"""
|
|
|
加载所有的sid到List结构，从缓存队列取sid
|
|
|
:return:
|
|
|
"""
|
|
|
valid_sid = []
|
|
|
keys = self.redis_cli.keys(f'{self.redis_key_prefix}:*')
|
|
|
for key in keys:
|
|
|
# 获取所有的信息
|
|
|
key_obj: dict = self.redis_cli.hgetall(key)
|
|
|
if key_obj.get("status") == "normal":
|
|
|
real_sid = key.rsplit(':', maxsplit=1)[-1]
|
|
|
valid_sid.append(real_sid)
|
|
|
self.redis_cli.lpush(self.cookiepool_cache_key, real_sid)
|
|
|
return valid_sid
|
|
|
|
|
|
def del_sid_from_redis(self):
|
|
|
self.redis_cli.delete(f'{self.cookiepool_cache_key}')
|
|
|
|
|
|
|
|
|
class A:
|
|
|
def __init__(self, redis_cli):
|
|
|
self.redis_cli = redis_cli
|
|
|
|
|
|
def load_keys(self, name):
|
|
|
return self.redis_cli.keys(r'cookie_pool:wos_sid:*')
|
|
|
|
|
|
def get_one_sid(self, name):
|
|
|
return self.redis_cli.rpoplpush(name)
|
|
|
|
|
|
|