socket 代码

# ！user/bin/env python3
# -*-coding: utf-8 -*-
__author__ = 'xxx'

import socket
import re

'http://image.baidu.com/search/index?tn=baiduimage&word=%E9%AC%BC%E7%81%AD%E4%B9%8B%E5%88%83%E5%A3%81%E7%BA%B8'

root = 'http://image.baidu.com/search/index?tn=baiduimage&word=%E9%AC%BC%E7%81%AD%E4%B9%8B%E5%88%83'

# 创建一个客户端
client = socket.socket()

# 连接百度
client.connect(('image.baidu.com', 80))

# 构造报文
request = 'GET /search/index?tn=baiduimage&word=%E9%AC%BC%E7%81%AD%E4%B9%8B%E5%88%83%E5%A3%81%E7%BA%B8 HTTP/1.0\r\nHost: image.baidu.com\r\n\r\n'

# 发送消息给到百度
client.send(request.encode())

# 循环接受百度返回的数据
res = b''
data = client.recv(1024)

while data:
    res += data
    data = client.recv(1024)  # 最后一次 读取的时候 会返回一个空

image_content = re.findall(r'thumbURL":"(.*?)"', res.decode(), re.S)

# print(image_content)
num = 0
for image_url in image_content[:-4]:
    host = image_url.split('//')[-1].split('.com')[0]
    path = image_url.split('//')[-1].split('.com')[-1]
    image_client = socket.socket()
    print(host)
    image_client.connect((host + '.com', 80))
    image_request = 'GET {} HTTP/1.0\r\nHost: {}\r\nReferer: {}\r\n\r\n'.format(path, host + '.com', root)
    # image_request = 'GET {} HTTP/1.0\r\nHost: {}\r\n\r\n'.format(path, host + '.com')
    image_client.send(image_request.encode())
    res = b''
    data = image_client.recv(1024)

    while data:
        res += data
        data = image_client.recv(1024)

    print(res)

    image_content = re.findall(b'\r\n\r\n(.*)', res, re.S)[0]
    # image_file_name = root.split('/')[-1]

    with open(str(num) + '.jpg', 'wb') as f:
        f.write(image_content)

    num += 1