168 lines
5.8 KiB
Python
168 lines
5.8 KiB
Python
# -*- coding: utf-8 -*-
|
||
|
||
# Define here the models for your spider middleware
|
||
#
|
||
# See documentation in:
|
||
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
|
||
import pdb
|
||
import time
|
||
import json
|
||
import requests
|
||
|
||
from scrapy.http import HtmlResponse
|
||
from selenium.common.exceptions import TimeoutException
|
||
from selenium import webdriver
|
||
from selenium.webdriver.support.wait import WebDriverWait
|
||
from scrapy_splash import SplashRequest
|
||
|
||
from scrapy import signals
|
||
|
||
|
||
class ZhihuSpiderMiddleware(object):
|
||
# 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.
|
||
|
||
print('process_spider_input')
|
||
|
||
# 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.
|
||
|
||
print('process_spider_output')
|
||
|
||
# Must return an iterable of Request, dict 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 Response, dict
|
||
# or Item objects.
|
||
pass
|
||
|
||
def process_start_requests(self, start_requests, spider):
|
||
# Called with the start requests of the spider, and works
|
||
# similarly to the process_spider_output() method, except
|
||
# that it doesn’t have a response associated.
|
||
|
||
print('process_start_requests')
|
||
|
||
|
||
# Must return only requests (not items).
|
||
for r in start_requests:
|
||
yield r
|
||
|
||
def spider_opened(self, spider):
|
||
spider.logger.info('Spider opened: %s' % spider.name)
|
||
|
||
|
||
class ZhihuDownloaderMiddleware(object):
|
||
# 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 ZhihuChromeMiddleware(object):
|
||
CHROME_DRIVER_PATH = r'/Users/guange/.bin/chromedriver'
|
||
COOKIES = {
|
||
'z_c0': '2|1:0|10:1543151267|4:z_c0|92:Mi4xcFpjMkFBQUFBQUFBWUdnWG5naDZEaWNBQUFDRUFsVk5veXNpWEFELWM4WHU0b3c3anJvR3hobzhvMEpIR004b2xB|aada1968c0f5284002a0bbb552b95af6e87cf3848acc15adfe6d91ed4d9151d8'}
|
||
|
||
def __init__(self):
|
||
options = webdriver.ChromeOptions()
|
||
# options.add_argument('--headless')
|
||
options.add_argument('--window-size=1366,768')
|
||
options.add_argument('--blink-settings=imagesEnabled=false')
|
||
SERVICE_ARGS = ['--load-images=false', '--disk-cache=true', '--ignore-ssl-errors=true']
|
||
self.driver = webdriver.Chrome(chrome_options=options, service_args=SERVICE_ARGS,
|
||
executable_path=self.CHROME_DRIVER_PATH)
|
||
self.driver.set_page_load_timeout(30)
|
||
self.wait = WebDriverWait(self.driver, 10)
|
||
|
||
def process_request(self, request, spider):
|
||
self.driver.get(request.url)
|
||
self.driver.execute_script("scroll(0, 1000);")
|
||
time.sleep(1)
|
||
rendered_body = self.driver.page_source
|
||
return HtmlResponse(request.url, body=rendered_body, encoding="utf-8")
|
||
|
||
def spider_closed(self, spider, reason):
|
||
print('驱动关闭')
|
||
self.driver.close()
|
||
|
||
|
||
class RandomProxyMiddleware(object):
|
||
_ip_lists = []
|
||
|
||
def get_ip(self):
|
||
if len(self._ip_lists) <= 0:
|
||
r = requests.get('http://bigdata1.educoder.net/myapp/api/proxys.json')
|
||
self._ip_lists = json.loads(r.text)
|
||
|
||
data = self._ip_lists.pop()
|
||
return "http://%s:%d" % (data['ip'], data['port'])
|
||
|
||
|
||
def process_request(self, request, spider):
|
||
if isinstance(request, SplashRequest):
|
||
ip = self.get_ip()
|
||
print(ip)
|
||
request.meta['splash']['args']['proxy'] = ip
|
||
# request.meta['proxy'] = ip |