import requests
import re
url = f'https://m.bcoderss.com/tag/漫画/page/1/'
# 模拟浏览器 --> headers 请求头
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
# 发送请求
response = requests.get(url=url, headers=headers)
<Response [200]> 表示请求成功
提取详情页url地址
img_info = re.findall('<li><a target="_blank" href="(.*?)" alt="(.*?)" title=".*?">', response.text)
for循环遍历 把列表里面元素 一个一个提取出来
for img, title in img_info:
html_data = requests.get(url=img, headers=headers).text
# 提取原图url地址
img_url = re.findall('<img alt=".*?" title=".*?" src="(.*?)">', html_data)[0]
获取二进制数据
img_content = requests.get(url=img_url).content
替换特殊字符
img_title = title + img_url.split('/')[-1]
img_title = re.sub(r'[\/:*?:<>|]', '_', img_title)
with open('img漫画\\' + img_title, mode='wb') as f:
f.write(img_content)
print(img_url, img_title)