用Python爬取文本信息

最新推荐文章于 2024-07-21 21:39:32 发布

小鸡仔_orz

最新推荐文章于 2024-07-21 21:39:32 发布

阅读量2.9k

点赞数

分类专栏： Python 文章标签： Python 爬虫

Python 专栏收录该内容

13 篇文章 0 订阅

订阅专栏

import requests
import re
import time

headers={
        'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.638.0 Safari/534.16'
        }
res=requests.get('http://www.kugou.com/yy/rank/home/%7B%7D-8888.html')
f=open('E:/doupo.txt','a+')
def get_info(url):
    res=requests.get(url,headers=headers)
    contexts=re.findall('<p>(.*?)</p>',res.content.decode('utf-8'),re.S)
    for context in contexts:
        f.write(context+'\n')
        
if __name__ == '__main__':
    urls=['http://www.doupoxs.com/doupocangqiong/{}.html'.format(str(i))
    for i in range(2,24)]
    for url in urls:
        get_info(url)
    time.sleep(2)
print('{}'.format(res))
f.close()

import requests
import re
import time

headers={
'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.638.0 Safari/534.16'
}#模拟浏览器抓取数据
res=requests.get('http://www.kugou.com/yy/rank/home/%7B%7D-8888.html')
f=open('E:/doupo.txt','a+')#以追加的方式创建文档
def get_info(url):
res=requests.get(url,headers=headers)
contexts=re.findall('<p>(.*?)</p>',res.content.decode('utf-8'),re.S)#用正则表达式匹配要查找的内容
for context in contexts:
f.write(context+'\n')

if __name__ == '__main__':
urls=['http://www.doupoxs.com/doupocangqiong/{}.html'.format(str(i))
for i in range(2,24)]
for url in urls:
get_info(url)
time.sleep(2)
print('{}'.format(res))
f.close()