import requests import re if __name__=='__main__': headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36 Edg/88.0.705.56'} url='https://www.qiushibaike.com/imgrank/' #使用通用爬虫对URL对应的一整张页面进行爬取 page_text=requests.get(url=url,headers=headers).text #使用聚焦爬虫对页面中所有图片进行解析、提取 ex='<div class="thumb"><a href=".*?"target="_blank"><img src=".*?"alt=".*?"class="illustration" width="100%" height="auto"></a></div>' img_src_list=re.findall(ex,page_text,re.S) print(img_src_list)
D:\phython\anaconda\python.exe D:/phython/pycham/练习/爬虫练习/聚焦爬虫.py
[]
Process finished with exit code 0