用PHP尝试了半天都不行，网上找的python代码也不行，满足我不了我爬取图片的场景，而后搜集了一些资料，最后发现用request模块下的get方法和可以携带header头，然后将获取的对象直接写入图片就行了
原来没有防盗链的可以直接使用urllib模块中的request.urlretrieve方法保存图片到本地，但是现在很多图片网站使用了图床和第三方存储服务器，这样通过nginx的防盗链就无法直接下载图片，需要在浏览器的header头中仿造Referer和User-Agent，下面写了一段简单的代码仅供参考，下面是主要代码，稍微改改就能抓取大多数网站图片了，都是美女图片网，不好意思了！
#!/usr/bin/python3
#coding:utf-8
from urllib import request
import requests
import ssl
import re
import random
def getImg(html):
ssl._create_default_https_context = ssl._create_unverified_context
response = request.urlopen(html)
response = response.read()
response = response.decode('utf-8')
reg1 = r'<h1 class="center">(.*)\(1/(.*)\)</h1>'
page_src = re.compile(reg1)
page = re.findall(page_src, response)
reg2 = r'<img src="(.*)" alt="(.*)" />'
img_src = re.compile(reg2)
img_list = []
i = 1
while True:
if i == 1:
response = request.urlopen(html)
response = response.read()
response = response.decode('utf-8')
img = re.findall(img_src, response)
img_list.append(img[0][0])
if i > 1:
html_more = html.replace(".html", "_%s.html" % str(i))
response_more = request.urlopen(html_more)
response_more = response_more.read()
response_more = response_more.decode('utf-8')
img = re.findall(img_src, response_more)
img_list.append(img[0][0])
if i >= int(page[0][1]):
break
i = i + 1
return img_list
def downImg(img_list):
ssl._create_default_https_context = ssl._create_unverified_context
headers = {
'Referer':'http://www.uumnt.cc/',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
for p in img_list:
img = requests.get(p, headers=headers)
num = random.randint(10000, 99999)
with open("img/%d.jpg" % num, 'wb') as f:
f.write(img.content)
if "__main__" == __name__:
html = r"https://www.uumtu.com/xinggan/30086.html"
img_list = getImg(html)
downImg(img_list)下面几个图片大站的采集脚本已经写好，可以直接拿走不谢
