第三十二节 selenium爬取拉勾网

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from lxml import etree
import time


class lagou():

    def __init__(self):
        self.browers_path = r'C:UsersAdministratorAppDataLocal360ChromeChromeApplication360chrome.exe'
        self.chrome_option = Options()
        self.chrome_option.binary_location = self.browers_path
        self.driver = webdriver.Chrome(options=self.chrome_option)
        self.url = "https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput="

    def run(self):
        all_list = []
        sourse = self.driver.get(self.url)
        elementi= self.driver.find_element_by_xpath('//div[@class="body-btn"]')
        elementi.click()
        time.sleep(5)
        sourse = self.driver.page_source
        self.parse_path(sourse)
        # all_list.extend(s)
        # return all_list

    def parse_path(self,sourse):
        position_list = []
        html = etree.HTML(sourse)
        links = html.xpath('//a[@class="position_link"]//@href')
        for link in links:
            self.xiangqingye(link)
        #     position_list.append(h)
        # return position_list

    def xiangqingye(self,ur):
        # self.driver.execute_script("window.open('https://www.lagou.com/jobs/6232081.html?show=23decdaefd344a719f63cfa436b063b8')" )
        self.driver.execute_script("window.open('%s')"%ur)
        self.driver.switch_to.window(self.driver.window_handles[1])
        time.sleep(2)
        xiang_source = self.driver.page_source
        html = etree.HTML(xiang_source)
        job_resqust_spans = html.xpath('//dd[@class="job_request"]//span')
        salary = job_resqust_spans[0].xpath('.//text()')[0].strip()
        city = job_resqust_spans[1].xpath('.//text()')[0].strip()
        workyears = job_resqust_spans[2].xpath('.//text()')[0].strip()
        position = {
            'salary':salary,
            'city':city,
            'workyears':workyears
        }
        print(position)
        time.sleep(1)
        self.driver.close()
        self.driver.switch_to.window(self.driver.window_handles[0])
        # print('aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa')

if __name__ == '__main__':
    lagou_shili = lagou()
    q = lagou_shili.run()
    print(q)

    # browers_driver.execute_script('window.open("https://www.douban.com")')
    # window_list = browers_driver.window_handles#获取窗口列表
    # browers_driver.switch_to.window(window_list[1])#将browers_driver的指针转移到指定的窗口
    # print(browers_driver.current_url)#打印browers_driver指向的窗口网址