正则解析:
- import re
- re.findall(正则表达式,网页源码数据,re.S)
import requests
import re
import os
from pprint import pprint
if __name__ == "__main__":
if not os.path.exists('./qiutuLibs'):
os.mkdir('./qiutuLibs')
url = 'https://www.qiushibaike.com/imgrank/'
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
}
page_text = requests.get(url=url, headers=headers).text
ex = '<div class="thumb">.*?<img src="(.*?)" alt.*?</div>'
img_scr_list = re.findall(ex, page_text, re.S)
pprint(img_scr_list)
for src in img_scr_list:
src = 'https:' + src
img_data = requests.get(url=src, headers=headers).content
img_name = src.split('/')[-1]
imgpath = './qiutuLibs/' + img_name
with open(imgpath, 'wb') as fp:
fp.write(img_data)
print(img_name, '下载成功')