'''将新浪新闻首页所有新闻爬取下来'''
import urllib.request
import urllib.error
import re
#模拟请求头
headers={
'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/49.0.2623.112 Safari/537.36"
}
#设置请求体
req=urllib.request.Request('https://news.sina.com.cn/',headers=headers)
response=urllib.request.urlopen(req)
data=response.read().decode('utf-8','ignore')
#正则表达式
pat='href="(http://news.sina.com.cn/.*?)"'
#新闻链接
urllists=re.findall(pat,data)
print(urllists)
for i in range(1,len(urllists)):
time.sleep(3)
try:
file="C:/Users/Administrator/Desktop/news/"+str(i)+".html"
urllib.request.urlretrieve(urllists[i],file)
except urllib.error.URLError as e:
if hasattr(e,'code'):
print(e.code)
if hasattr(e,'reason'):
print(e.reason)
将新浪新闻首页所有新闻爬取下来
最新推荐文章于 2023-12-23 15:52:36 发布