Python 3.x 使用Cookie通过scrapy请求更改货币

我正试图从中提取数据。下面是我为完成这项工作而编写的代码

cookies = {'.AspNetCore.Antiforgery.M6FGfmlbnTQ': 'CfDJ8A-eCRip5cVAs8-wkFU1H8dmFA0OIoxp6pQh1dcRvnpdNHKpKwFF2EhHSg5c-yqb-DriS6AIiwgnIpzyMiiphd42Un2v0-X6l8ePR4KkjG_CR2a_u6qrFOZNrRg0jrhliPOhyV6TKCtu6k-rn92lVMI',
 'uCurr': 'EUR'}

header = {'User-Agent': 'APIs-Google (+https://developers.google.com/webmasters/APIs-Google.html)',
 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 'X-Requested-With': 'XMLHttpRequest'}

formdata = {'query': 'AR-LCAAAAAAAAApNjr0KwkAQhN9l6gvsXn5M1iqohZUSkweImqjgD6LYhLy7c0UgcMUcM7PzDXjBBrSwRByOMHjxGkkWSVKrmggfHE4zR3XunGGxjwuHbhI9LE8K73CZxJXtVblm-ka1aSqqO8znDg-YZqkLGBo7vOmL0m7DYveMmgM_Hx7imS8rWpDzB1swQmqU22q_q-rQCPSBYBlGw0IqzOk4_gFLkZV45QAAAA2',
 'discount': 'AG51bGw1',
 '__RequestVerificationToken': 'CfDJ8A-eCRip5cVAs8-wkFU1H8fDgaTCPGKJ6FVhqBSItqEvJHfZlsE0bsh4EKYxRKIpb3CDhue0bRj0jOgsLjyHTIvvEolzWwGt1CDfRlgnXrfO8NZiEE3ZQhIyeVShd5-AxG-QhQp4zSE3WeWo7Fr40DI'}

url = 'https://www.carflexi.com/data/getDeals'

In [47]: fetch(scrapy.FormRequest(url, method='POST', headers=header, formdata=formdata,cookies = cookies))                                           
2021-04-25 19:21:11 [scrapy.core.engine] DEBUG: Crawled (200) <POST https://www.carflexi.com/data/getDeals> (referer: None)

---

Proxy nova是一个免费的代理提供商，我们正在尝试在生成请求之前从该网站获取代理地址。我使用selenium获取代理IP

import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
class CarflexiSpider(scrapy.Spider):
    name = 'carflexi'
    allowed_domains = ['www.carflexi.com']
    start_urls = ['https://www.carflexi.com/data/getDeals']

    def __init__(self):
        self.proxy_adress_is = self.proxy_adress()

    def proxy_adress(self):
        url = "https://www.proxynova.com/proxy-server-list/country-de/"
        opts = Options()
        opts.add_argument('--headless')
        driver = webdriver.Chrome(options=opts,executable_path="chromedriver")
        driver.get(url)
        time.sleep(3)
        proxy_ip = driver.find_element_by_xpath('//*[@id="tbl_proxy_list"]/tbody[1]/tr[1]/td[1]/abbr').text
        proxy_ip = proxy_ip.replace(",","").strip()
        proxy_port = driver.find_element_by_xpath('//*[@id="tbl_proxy_list"]/tbody[1]/tr[1]/td[2]').text
        proxy_port = proxy_port.replace(",","").strip()
        driver.close()
        return proxy_ip+":"+proxy_port

    def parse(self, response):
        url = 'https://www.carflexi.com/data/getDeals'
        request = scrapy.Request(
                url, callback=self.parse_product)
        request.meta['proxy'] = self.proxy_adress_is
        yield request

    def parse_product(self,response):
        pass

proxy_Address功能将允许您连接到德国IP，然后您可以获得欧元价格

---

我没有使用表单请求。您将根据脚本进行更改。

这称为地理围栏。web服务器正在检查连接到它的客户端的IP地址，并将其与位于该国家/地区内的已知IP范围列表进行比较。你不能得到欧元，你必须使用VPN或代理。如果您想使用代理，我将帮助您提供免费的selenium代理脚本。@MuratDemir请共享该脚本。另外，是否有任何方法可以更改本地计算机的货币/国家/地区以避开此问题？您可以使用代理进行此操作again@MuratDemir你能分享你的剧本吗？当然，让我为你准备

import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
class CarflexiSpider(scrapy.Spider):
    name = 'carflexi'
    allowed_domains = ['www.carflexi.com']
    start_urls = ['https://www.carflexi.com/data/getDeals']

    def __init__(self):
        self.proxy_adress_is = self.proxy_adress()

    def proxy_adress(self):
        url = "https://www.proxynova.com/proxy-server-list/country-de/"
        opts = Options()
        opts.add_argument('--headless')
        driver = webdriver.Chrome(options=opts,executable_path="chromedriver")
        driver.get(url)
        time.sleep(3)
        proxy_ip = driver.find_element_by_xpath('//*[@id="tbl_proxy_list"]/tbody[1]/tr[1]/td[1]/abbr').text
        proxy_ip = proxy_ip.replace(",","").strip()
        proxy_port = driver.find_element_by_xpath('//*[@id="tbl_proxy_list"]/tbody[1]/tr[1]/td[2]').text
        proxy_port = proxy_port.replace(",","").strip()
        driver.close()
        return proxy_ip+":"+proxy_port

    def parse(self, response):
        url = 'https://www.carflexi.com/data/getDeals'
        request = scrapy.Request(
                url, callback=self.parse_product)
        request.meta['proxy'] = self.proxy_adress_is
        yield request

    def parse_product(self,response):
        pass