crawl——入门

一、介绍

1 比如:百度是个大爬虫
2 搜索引擎

  seo不花钱 优化:建外链,加关键字,曝光率高,伪静态
  sem花钱优化,百度自己优化

3 模拟浏览器发送http请求---(请求库)(频率,cookie,浏览器头。。js反扒,app逆向)(抓包工具)-----》从服务器取回数据-----》
  解析数据--(解析库)(反扒)----》入库(存储库,) 4 爬虫协议:

二、requests模块

0 urllib 内置库,发送http请求,比较难用,requests是基于这个库的写的
1 requests,目前应用非常广泛的请求库
2 request-html库(对request,bs4,lxml等的二次封装)

3 User-Agent:请求头中标志是什么客户端发送的请求
4 Referer:上次请求的地址

 5 requests模块的使用(requests-html)
    -get 请求:加头,get请求参数,转码
    -post:请求头,cookie,post携带数据
    -响应对象的属性
    -其它用法:使用代理
    -收费,免费
    -高匿,透明

2.1 发送get请求

携带数据,携带头,携带cookie。。。

演示

import requests
# res=requests.get('https://www.cnblogs.com/')
# # print(res.text)  # 文本内容
# print(res.content) # 二进制内容 视频,图片  res.iter_content()


## 携带参数
# header={
#     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36'
# }
#https://www.sogou.com/web?query=%E7%87%95%E7%AA%9D
# # res=requests.get('https://www.baidu.com/s?wd=帅哥',headers=header)
# res=requests.get('https://www.baidu.com/s',headers=header,params={'wd':'老奶奶'})
#
# with open('baidu.html','wb') as f:
#     f.write(res.content)
# # print(res.text)


#### url编码和解码
from urllib.parse import urlencode,unquote
# wd='燕窝'
# encode_res=urlencode({'k':wd},encoding='utf-8')
# print(encode_res)

res=unquote('%E7%87%95%E7%AA%9D')
print(res)



### 携带头
'''
Host  :
Referer :大型网站通常都会根据该参数判断请求的来源
User-Agent: 客户端
Cookie :Cookie信息虽然包含在请求头里,但requests模块有单独的参数来处理他,headers={}内就不要放它了
# cookie携带的两种方式,如果是字符串形式,就放在请求头中
如果是字典,cookiejar的对象,就放在参数中cookies=字典,cookiejar的对象
'''

# header={
#     'Cookie':'BIDUPSID=BAA91359911D4514C92ABD22B88961AE; PSTM=1601026753; MCITY=-289%3A; BD_UPN=12314753; sug=3; sugstore=0; ORIGIN=0; bdime=0; H_WISE_SIDS=164576_164894_161282_165717_163389_156287_163806_159613_162897_155226_165552_151532_165328_159530_159937_162434_160878_161125_164299_164987_164692_127969_156929_164163_160246_165292_164941_163979_165236_164621_160276_131423_164148_128701_165203_165424_161568_107312_164812_163412_165375_160574_161965_161674_163270_144966_164259_162186_154213_161237_158640_160980_164131_161885_162268_161771_164451_162643_165471_162156_110085_162020_163569_163567_164960_165074_163274_164128_165144_165155_165647_165711; __yjs_duid=1_5cf7a7f565d2f9cacef83d808d8eb0c01610527765679; BAIDUID=EA290B9A7A371E91762170324A4ED8C0:FG=1; BDSFRCVID=R60OJexroG3VeHne34XvvrEMkvqMFyTTDYLEJs2qYShnrsPVJeC6EG0PtoWQkz--EHtdogKK0gOTH6KF_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF=JJkO_D_atKvjDbTnMITHh-F-5fIX5-RLfbreBh7F54nKDp0R3xRi0tQyhJJZ-Jj4BC3MahvKQDOxsMTsQqOr34tn2foyKt6lQe_JLqTN3KJmfKn1bUbA5DrXWxvM2-biWbRM2MbdJqvP_IoG2Mn8M4bb3qOpBtQmJeTxoUJ25DnJhhCGe6t5D5J0jN-s-bbfHDJK0b7aHJOoDDv40MQcy4LbKxnxJhKLtIo-oKbob4QKsq6cbURvD--g3-OkWUQ7Q2QCBI3mtJ3KsxQTyb3HQfbQ0hOyKfjxX5ILaKbH2R7JOpkxbUnxy5KUQRPH-Rv92DQMVU52QqcqEIQHQT3m5-5bbN3ut6IDfKbKWbvqajrDHJTg5DTjhPrM0GDjWMT-MTryKKOC5ln_eD8mWbj-KxLIMpjDWx58QNnRhlRNWt8KqfTbM-TKKp8ZyxomtfQxtNRJWM3l2-FVKq5S5-OobUPUDMJ9LUkqW2cdot5yBbc8eIna5hjkbfJBQttjQn3hfIkj2CKLK-oj-D89ejub3j; ab_sr=1.0.0_MmE0YjM2NDEzZTYyMDc3MzcyOGRmY2FlZTUwODAxYmU0MGZkNTQxMGZjYmIzNGMyYTQwOTY1OGRlMGZjYWI3MjMwYjIxMWM0NGIzNDljZWNmYWI1NDljNmE3YjIyN2Nm; H_PS_PSSID=33423_33440_33344_33284_33286_33395_33463_33414_26350; H_PS_645EC=72dfrtzn7c42D9bDsI6pLpQGO5zBgUgpsueKbELHa2yRddAFDA%2FhwY0FWkg; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598'
# }
# res=requests.get('https://www.baidu.com/',cookies='',headers=header)

2.2 发送post请求

 携带数据,携带头,携带cookie

演示

import requests

## post请求携带数据
# res=requests.post('地址',headers=字典,cookie=对象,params='放在链接中',
#                   data='字典,放在请求体中',json='json格式字符串,放到请求体中')

''''
#如果我们自定义请求头是application/json,并且用data传值, 则服务端取不到值
requests.post(url='',
              data={'':1,},
              headers={
                  'content-type':'application/json'
              })

requests.post(url='',
              json={'':1,},
              ) #默认的请求头:application/json
'''


## session对象,自动处理cookie,不需要人为处理cookie
## 一旦登录成功,以后,不需要手动携带cookie了,直接使用session对象发送请求,会自动携带


# session=requests.session()
#
# data = {
#     'username': '616564099@qq.com',
#     'password': 'lqz123',
#     'captcha': '123',
#     'remember': 1,
#     'ref': 'http://www.aa7a.cn/',
#     'act': 'act_login',
# }
# header = {
#     'Referer': 'http://www.aa7a.cn/user.php?&ref=http%3A%2F%2Fwww.aa7a.cn%2Fuser.php%3Fact%3Dlogout',
#     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36'
# }
# res = session.post('http://www.aa7a.cn/user.php', headers=header,data=data)
#
#
# res=session.get('http://www.aa7a.cn/')
# print('616564099@qq.com' in res.text)

2.3 高级用法

使用代理,上传文件,超时设置

演示

import requests
### SSL Cert Verification(了解即可)

## 方式一
# respone=requests.get('https://www.12306.cn',verify=False) #不验证证书,报警告,返回200
#
# # 手动携带证书
# import requests
# respone=requests.get('https://www.12306.cn',
#                      cert=('/path/server.crt',
#                            '/path/key'))
# print(respone.status_code)


#超时设置
# import requests
# respone=requests.get('https://www.baidu.com',
#                      timeout=0.01)
# print(respone.text)

# 认证设置(了解)
# import requests
# from requests.auth import HTTPBasicAuth
# r=requests.get('xxx',auth=HTTPBasicAuth('user','password'))
# print(r.status_code)


# 异常处理
# import requests
# from requests.exceptions import * #可以查看requests.exceptions获取异常类型
#
# try:
#     r=requests.get('http://www.baidu.com',timeout=0.00001)
# # except ReadTimeout:
# #     print('===:')
# # except ConnectionError: #网络不通
# #     print('-----')
# # except Timeout:
# #     print('aaaaa')
#
# except Exception as e:
#     print(e)



## 上传文件
# import requests
# files={'file':open('a.jpg','rb')}
# respone=requests.post('http://httpbin.org/post',files=files)
# print(respone.status_code)


## 代理设置

import requests
# 免费代理(不稳定)
# 收费代理(稳定)
proxies={
    'HTTP':'117.95.200.239:9999',
}
respone=requests.get('https://www.12306.cn',
                     proxies=proxies)

print(respone.status_code)

# 写一个django,取出访问者的ip地址,使用requests,加代理模块访问

2.4 知识拓展——高匿名代理和透明代理

# 高匿名代理和透明代理
# 高匿:服务端取不到真实的ip
# 透明:服务端可以取到真实的ip地址  请求头中:X-Forwarded-For   Meta

# 代理池:搞一堆代理,放到列表中,每次发请求,随机出一个(也有开源的代理池,最好用付费的,这样稳定)

2.5 测试代理

import requests

proxies={
    'http':'139.224.19.30:3128',
}
#给12306网发送请求
# respone=requests.get('https://www.12306.cn',proxies=proxies)
# print(respone) #<Response [200]>
# res=requests.get('http://101.133.225.166:8000/test/',proxies=proxies)#因为用的是免费的代理,有时候不能用或者不稳定
 res=requests.get('http://101.133.225.166:8000/test/')#139.227.249.148  print(res.text)

# 后端代码
def test(request):
ip=request.META.get('REMOTE_ADDR')
print(ip)
return HttpResponse(ip)

2.6 响应对象的方法

import requests
respone=requests.get('https://www.autohome.com.cn/shanghai/')
# respone属性
# print(respone.text)  # 文本内容
# print(respone.content)  # 二进制

# print(respone.status_code) # 状态码
# print(respone.headers)    # 响应头
# print(type(respone.cookies) )   # cookie对象  RequestsCookieJar
from requests.cookies import RequestsCookieJar
# print(respone.cookies.get_dict()) # cookie对象转成字典
# print(respone.cookies.items())



# print(respone.url)    # 请求地址
# print(respone.history) # 当你访问一个网站,有30x,重定向之前的地址,

print(respone.encoding) # 网站编码

# respone.encoding='gb2312'
# print(respone.text)
#
# #关闭:response.close()
# from contextlib import closing
# with closing(requests.get('xxx',stream=True)) as response:
#     for line in response.iter_content():
#     pass

## 解析json


# import json
# json.loads(respone.text)
# respone.json()

 

posted @ 2021-01-19 18:50  1024bits  阅读(582)  评论(0编辑  收藏  举报