爬虫 http原理,梨视频,github登陆实例,requests请求参数小总结

回顾:http协议基于请求响应的方式，请求：请求首行 请求头{'keys':vales} 请求体 ；响应:响应首行，响应头{'keys':'vales'}，响应体。

import socket

sock=socket.socket()
sock.bind(("127.0.0.1",8808))
sock.listen(5)

while 1:
    print("server waiting.....")
    conn,addr=sock.accept()
    data=conn.recv(1024)
    print("data", data)

    # 读取html文件
    with open("login.html","rb") as f:
        data=f.read()

    conn.send((b"HTTP/1.1 200 OK\r\nContent-type:text/html\r\n\r\n%s"%data))
    conn.close()

基于socket的浏览器交互

'''
    GET请求
    # 请求首行
    GET / HTTP/1.1\r\n
    # get请求后面的参数
    b'GET /?name=wd&age=11 HTTP/1.1\r\n
    # 请求头
    Host: 127.0.0.1:8008\r\n
    Connection: keep-alive\r\n
    Cache-Control: max-age=0\r\n
    Upgrade-Insecure-Requests: 1\r\n
    User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64)
    AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181Safari/537.36\r\n
Accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8\r\nAccept-Encoding: gzip, deflate, br\r\n
Accept-Language: zh-CN,zh;q=0.9\r\n Cookie:csrftoken=7xx6BxQDJ6KB0PM7qS8uTA892ACtooNbnnF4LDwlYk1Y7S7nTS81FBqwruizHsxF\r\n\r\n'
    # 请求体（get请求，请求体为空）
    '''
   b''
    '''
    POST请求
    # 请求首行
    b'POST /?name=wd&age=11 HTTP/1.1\r\n
    # 请求头
    Host: 127.0.0.1:8008\r\n
Connection: keep-alive\r\n
Content-Length: 21\r\n
Cache-Control: max-age=0\r\n
Origin: http://127.0.0.1:8008\r\n
Upgrade-Insecure-Requests: 1\r\n
Content-Type: application/x-www-form-urlencoded\r\n
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36\r\n
Accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8\r\n
Referer: http://127.0.0.1:8008/?name=lqz&age=18\r\n
Accept-Encoding: gzip, deflate, br\r\n
Accept-Language: zh-CN,zh;q=0.9\r\n
Cookie:csrftoken=7xx6BxQDJ6KB0PM7qS8uTA892ACtooNbnnF4LDwlYk1Y7S7nTS81FBqwruizHsxF\r\n\r\n'
    # 请求体
    b'name=wd&password=11'

    '''
 

请求

b"HTTP/1.1 200 OK\r\n
Content-type:text/html\r\n\r\n
%s"%data

响应

http原理

点击详情

梨视频案例

#返回数据3种格式
#1.text                    匹配需要的东西
#2.content(二进制)    保存成图片,视频等
#3.json                    反序列化成字典或列表

#下载功能
def download(videos,title):
    if not os.path.exists('video'):
        os.mkdir('video')
    path=os.path.join('video',title)+'.mp4'
    res=requests.get(videos)
    with open(path,'wb') as f:
        f.write(res.content)

#起线程执行执行
if __name__ == '__main__':
    from concurrent.futures import ThreadPoolExecutor
    p=ThreadPoolExecutor(10)
    for i in parser_index(get_index()):
        dic=video_info(get_video(i))
        print(dic)
        p.submit(download,dic['video'],dic['title'])
    p.shutdown(wait=True)

#注意问题:梨视频下滑加载视频（是根据url的参数,例如分类下的视频显示多少）

github登陆实例

#get请求登陆页面 获取csrf随机字符串和cookies

#post请求登陆操作 携带csrf,输入的用户名密码等(请求体数据) 和 cookies,user-agent,referer等(请求头数据) 必须数据

数据是请求体还是请求头数据？ （我的理解是比如ajax里的data,django的返回数据都是请求体的数据. request.set_cookies('islogin':'true') request对象的数据为请求头的）

"""
1.请求登陆页面 获取token cookie
2.发生登陆的post请求,将用户名密码 和token 放在请求体中,cookie放在请求头中

"""
import requests
import re
login_url = "https://github.com/login"
#浏览器标识
headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"}
#请求登陆页面
res1 = requests.get(login_url,headers=headers)

print(res1.status_code)
# 从响应体中获取token
token = re.search('name="authenticity_token" value="(.*?)"',res1.text).group(1)

# 保存cookie
login_cookie = res1.cookies.get_dict()
print(login_cookie)

# 发送登陆请求
res2 = requests.post("https://github.com/session",
              headers={
                  "user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"},
              cookies = login_cookie,
              data={
                "commit": "Sign in",
                "utf8": "✓",
                "authenticity_token": token,
                "login": "xxxxxxxxxxx",
                "password": "xxxxxxxxxxx"},
                # 是否允许自动重定向
                allow_redirects = False)
print(res2.status_code)

# 用户登录成功后的cookie
user_cookie = res2.cookies.get_dict()

# 携带用户cookies访问主页
res3 = requests.get("https://github.com/settings/profile",cookies = user_cookie,headers = headers)
print(res3.status_code)
print(res3.text)
# "https://github.com/settings/profile"

requests请求参数小总结

#get请求参数
kwd = "吴秀波出轨门"
url = "https://www.baidu.com/s"
requests.get(url,headers=headers,params={"wd":kwd})

#post请求参数
requests.post("https://github.com/session",
              headers={
                  "user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"},
              cookies = login_cookie,
              data={
                "commit": "Sign in",
                "utf8": "✓",
                "authenticity_token": token,
                "login": "ssssss",
                "password": "ssssss"},
                # 是否允许自动重定向
                allow_redirects = False)
#返回值处理
# response.cookies.get_dict() #获取cookies
# response.status_code # 状态码
# response.text # 将结果以文本的形式返回
# response.content # 将结果以二进制的方式返回
# response.json() # 将数据直接反序列化得到字典或是列表

主要代码内容