mac python+selenium+阿布雲 爬取拉鉤網

廢話不多說直接上代碼

import time
import csv
from selenium import webdriver
import string
import zipfile
from lxml import etree

# 代理服務器
proxyHost = "http-dyn.abuyun.com"
proxyPort = "9020"

# 代理隧道驗證信息
proxyUser = "HD2A47190U2xxxx"
proxyPass = "CB1FDB9303ABxxxx"


def create_proxy_auth_extension(proxy_host, proxy_port,
                                proxy_username, proxy_password,
                                scheme='http', plugin_path=None):
    if plugin_path is None:
        plugin_path = '{}_{}@http-dyn.abuyun.com_9020.zip'.format(proxy_username, proxy_password)

    manifest_json = """
       {
           "version": "1.0.0",
           "manifest_version": 2,
           "name": "Abuyun Proxy",
           "permissions": [
               "proxy",
               "tabs",
               "unlimitedStorage",
               "storage",
               "<all_urls>",
               "webRequest",
               "webRequestBlocking"
           ],
           "background": {
               "scripts": ["background.js"]
           },
           "minimum_chrome_version":"22.0.0"
       }
       """

    background_js = string.Template(
        """
        var config = {
            mode: "fixed_servers",
            rules: {
                singleProxy: {
                    scheme: "${scheme}",
                    host: "${host}",
                    port: parseInt(${port})
                },
                bypassList: ["foobar.com"]
            }
          };

        chrome.proxy.settings.set({value: config, scope: "regular"}, function() {});

        function callbackFn(details) {
            return {
                authCredentials: {
                    username: "${username}",
                    password: "${password}"
                }
            };
        }

        chrome.webRequest.onAuthRequired.addListener(
            callbackFn,
            {urls: ["<all_urls>"]},
            ['blocking']
        );
        """
    ).substitute(
        host=proxy_host,
        port=proxy_port,
        username=proxy_username,
        password=proxy_password,
        scheme=scheme,
    )

    with zipfile.ZipFile(plugin_path, 'w') as zp:
        zp.writestr("manifest.json", manifest_json)
        zp.writestr("background.js", background_js)

    return plugin_path


proxy_auth_plugin_path = create_proxy_auth_extension(
    proxy_host=proxyHost,
    proxy_port=proxyPort,
    proxy_username=proxyUser,
    proxy_password=proxyPass)

option = webdriver.ChromeOptions()
prefs = {
'profile.managed_default_content_settings.images': 2,
'permissions.default.stylesheet': 2
}

option.add_argument("--start-maximized")
option.add_extension(proxy_auth_plugin_path)
option.add_experimental_option('prefs', prefs)
path = '/Users/lin/Desktop/demo/chromedriver'
driver = webdriver.Chrome(executable_path=path,chrome_options=option)

link = 'https://www.lagou.com/'

driver.get(link)

time.sleep(5)

# 搜索傳智播客
driver.find_element_by_id("search_input").send_keys("python")
# 點擊搜索按鈕
driver.find_element_by_id("search_button").click()


time.sleep(5)

pageSource = driver.page_source

et = etree.HTML(pageSource)

list_li = et.xpath('//*[@id="s_position_list"]/ul/li')

list_csvs = []

for i in list_li:

    headline = i.xpath('./div[1]/div[1]/div/a/h3/text()')[0] #標題

    place=i.xpath('./div[1]/div[1]/div[1]/a/span/em/text()')[0] #地方

    company=i.xpath('./div[1]/div[2]/div[1]/a/text()')[0] #公司

    pay=i.xpath('./div[1]/div[1]/div[2]/div/span/text()')[0]#薪資

    experience_background = i.xpath('./div[1]/div[1]/div[2]/div/text()[3]')#經驗學歷
    experience=experience_background[0].split('/')[0] #經驗
    background=experience_background[0].split('/')[1].replace('\t','').replace(' ','').replace('\n','') #經驗

    release = i.xpath('./div[1]/div[1]/div[1]/span/text()')[0] #發佈日期


    list_csvs.append([headline,place,company,pay,experience,background,release])


# python2可以用file替代open
with open("test.csv", "a") as csvfile:
    writer = csv.writer(csvfile)

    # 先寫入columns_name
    writer.writerow(["標題", "地點", "公司名稱","經驗",'薪資',"學歷",'發佈時間'])
    # 寫入多行用writerows
    writer.writerows(list_csvs)

結果：