python爬虫之利用Selenium+Requests爬取拉勾网

url="https://www.lagou.com/jobs/positionAjax.json?px=default&needAddtionalResult=false"
参数：
city=%E5%8C%97%E4%BA%AC  ==》城市
first=true  ==》无用
pn=1  ==》页数
kd=%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90  ==》商品关键词

def City_Page(self):
    City_Page={}
    url="https://www.lagou.com/jobs/allCity.html?keyword=%s&px=default&companyNum=0&isCompanySelected=false&labelWords="%(self.keyword)
    self.bro.get(url=url)
    sleep(30)
    print("开始获取城市及其最大页数")
    if "验证系统" in self.bro.page_source:
        sleep(40)
    html = etree.HTML(self.bro.page_source)
    city_urls = html.xpath('//table[@class="word_list"]//li/input/@value')
    for city_url in city_urls:
        try:
            self.bro.get(city_url)
            if "验证系统" in self.bro.page_source:
                sleep(40)
            city=self.bro.find_element_by_xpath('//a[@class="current_city current"]').text
            page=self.bro.find_element_by_xpath('//span[@class="span totalNum"]').text
            City_Page[city]=page
            sleep(0.5)
        except:
            pass
    self.bro.quit()
    data = json.dumps(City_Page)
    with open("city_page.json", 'w', encoding="utf-8")as f:
        f.write(data)
    return City_Page

def Params_List(self):
    with open("city_page.json", "r")as f:
        data = json.loads(f.read())
    Params_List = []
    for a, b in zip(data.keys(), data.values()):
        for i in range(1, int(b) + 1):
            params = {
                'city': a,
                'pn': i,
                'kd': self.keyword
            }
            Params_List.append(params)
    return Params_List

def Parse_Data(self,params):
    url = "https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false"
    header={
        'referer': 'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90?labelWords=&fromSearch=true&suginput=',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36',
        'cookie':''
    }
    try:
        text = requests.get(url=url, headers=header, params=params).text
        if "频繁" in text:
            print("操作频繁，已被发现 当前为第%d个params"%(i))
        data=json.loads(text)
        result=data["content"]["positionResult"]["result"]
        for res in result:
            with open(".//lagou1.csv", "a",encoding="utf-8") as f:
                writer = csv.DictWriter(f, res.keys())
                writer.writerow(res)
        sleep(1)
    except Exception as e:
        print(e)
        pass