def get_info(url):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
print('爬取失敗！')
def pict_paser(html):
list_jpg = re.findall(r'upload\\/files\\/2300\\/34888\\/(.*?)"',html)
for i in list_jpg:
print(i)
url = 'https://m-mhk8-com.mipcdn.com/i/res.fuduoduodb.com/upload/files/2300/34888/' + i
header = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4144.138 Safari/537.36',
'cookie':'id=224da28ac2c096||t=1588145311|et=730|cs=002213fd4856dd63944cf21e47'}
path = 'D://picss/' + url.split('/')[-1]
a = requests.get(url,timeout = 20,headers = header)
with open(path,'wb') as f:
f.write(a.content)
print('檔案保存成功')
uj5u.com熱心網友回復：
那就用selenium 扒轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/38501.html