爬虫入门--task04

一.爬取tx新闻

了解ajax加载
通过chrome的开发者工具，监控网络请求，并分析
用selenium完成爬虫
具体流程如下：
用selenium爬取https://news.qq.com/ 的热点精选

import time
from  selenium import webdriver
driver=webdriver.Chrome(executable_path="D:\chromedriver\chromedriver.exe")
driver.get("https://news.qq.com")
#了解ajax加载
for i in range(1,100):
    time.sleep(2)
    driver.execute_script("window.scrollTo(window.scrollX, %d);"%(i*200))

from bs4 import BeautifulSoup
html=driver.page_source
bsObj=BeautifulSoup(html,"lxml")
jxtits=bsObj.find_all("div",{"class":"jx-tit"})[0].find_next_sibling().find_all("li")

print("index",",","title",",","url")
for i,jxtit in enumerate(jxtits):
#     print(jxtit)
    
    try:
        text=jxtit.find_all("img")[0]["alt"]
    except:
        text=jxtit.find_all("div",{"class":"lazyload-placeholder"})[0].text
    try:
        url=jxtit.find_all("a")[0]["href"]
    except:
        print(jxtit)
    print(i+1,",",text,",",url)