warnings.warn('Selenium support for PhantomJS has been deprecated, please use headless '报错

问题:selenium已经放弃PhantomJS,建议使用火狐或者谷歌无界面浏览器。

解决方案1:

selenium版本降级

通过pip install selenium默认安装版本。 (通过pip show selenium显示版本)
将其卸载pip uninstall selenium,重新安装并指定版本号pip install selenium==2.48.0。

解决方案2:

使用别的浏览器,我这里使用的Chrome;

安装教程网上很多https://segmentfault.com/a/1190000013940356

实例:(采集北京市政百姓信件内容)

 


from lxml import etreeimport requestsimport csvfrom selenium import webdriverimport timeimport osfrom selenium.webdriver.chrome.webdriver import WebDriver#创建csvoutPath = D://xinfang_data.csvif (os.path.exists(outPath)): os.remove(outPath)fp = open(outPath, wt, newline=‘‘, encoding=utf-8) # 创建csvwriter = csv.writer(fp)writer.writerow((kind, time, processingDepartment, content))#请求头headers = { User-Agent:Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36}# 创建浏览器对象driver = webdriver.Chrome()# 得到网页信息def get_info(num): driver.get(url) driver.implicitly_wait(10) # 隐式等待n秒,解释JavaScript是需要时间的,如果短了就无法正常获取数据,如果长了浪费时间;implicitly_wait()给定时间智能等待 #driver.find_element_by_xpath(‘//*[@id="pageNum"]‘).clear() driver.find_element_by_id(pageNum).clear()#清除输入框 #driver.find_element_by_id(‘pageNum‘).send_keys(num) driver.find_element_by_xpath(//*[@id="pageNum"]).send_keys(num)#输入页数 driver.find_element_by_xpath(//*[@id="judgeFlag"]/a).click()#单击确认框 time.sleep(1)#一定要停一下,否则加载不出来一直输出第一页 #print(driver.current_window_handle)#当前页面句柄 html = driver.page_source #print(driver.page_source) return html#解析HTML文件,获取数据def get_data(html): selector = etree.HTML(html) infos=selector.xpath(//*[@id="mailul"]/div) for info in infos: kind=info.xpath(div[1]/a/font/text())[0] time=info.xpath(div[2]/div[1]/div[1]/text())[0] processingDepartment = info.xpath(div[2]/div[1]/div[2]/span/text())[0] content = info.xpath(div[1]/a/span/text())[0] #处理得到的字符串 parsekind=kind.strip().strip(·【).strip() #print(parsekind) parsetime=time.strip().strip(发起时间:).replace("-", "/") #print(parsetime) parsepd = processingDepartment.strip().strip(处理部门:) #print(parsepd) parsecontent = content.strip() #print(parsecontent) #写入csv writer.writerow((parsekind,parsetime,parsepd,parsecontent))if __name__ == __main__: url = http://www.beijing.gov.cn/hudong/hdjl/com.web.search.mailList.flow for i in range(1,1000): html=get_info(i) get_data(html) time.sleep(1)

View Code

 

相关文章