爬取腾讯新闻热点精选
腾讯新闻的 url:https://news.qq.com/
import time
from selenium import webdriver
from bs4 import BeautifulSoup
browser=webdriver.Chrome(r'D:\***\chromedriver.exe')
browser.get('https://news.qq.com/')
html=browser.page_source
soup=BeautifulSoup(html,"lxml")
# 这里只爬取了10条信息,如果需要100,就将10改成100
for i in range(1,10):
time.sleep(2)
browser.execute_script("window.scrollTo(window.scrollX, %d);"%(i*200))
a=soup.find_all("div",{"class":"jx-tit"})[0].find_next_sibling()
count = 0
for i in a.find_all("li"):
if len(i.find_all('h3')) > 0:
count = count + 1
print(count, ','+i.find_all('h3')[0].text+' '+i.find_all('a')[0]['href'])
browser.quit()
结果如图所示(格式有点错误):
爬取新浪新闻(国际新闻)的最新消息
新浪新闻(国际新闻)的url:https://news.sina.com.cn/world/
import requests
from selenium import webdriver
from bs4 import BeautifulSoup
browser = webdriver.Chrome(r'D:\***\chromedriver.exe')
url = "https://news.sina.com.cn/china/"
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0'
}
proxy = {
"http": "124.88.67.81:80"
}
def getHTMLText(url):
try:
r = requests.get(url,headers=headers,proxies= proxy,timeout = 30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
print('无法访问网页' + url)
if __name__ == "__main__":
url = "https://news.sina.com.cn/world/"
browser.get(url)
dome = getHTMLText(url)
soup = BeautifulSoup(dome,'html.parser')
count= 0
for i in soup.select('.news-item'):
if len(i.select('h2'))>0:
count = count + 1
print(count,','+ i.select('.time')[0].text+' '+i.select('h2')[0].text+' '+i.select('a')[0]['href'])
browser.quit()
结果如图所示: