爬虫

wusir

requests模块

import requests

"""
# 1. 方法
    requests.get
    requests.post 
    requests.put 
    requests.delete 
    ...
    requests.request(method='POST')
"""
# 2. 参数
"""
    2.1  url
    2.2  headers
    2.3  cookies
    2.4  params
    2.5  data，传请求体
            
            requests.post(
                ...,
                data={'user':'alex','pwd':'123'}
            )
            
            GET /index http1.1\r\nhost:c1.com\r\n\r\nuser=alex&pwd=123
            
    2.6  json，传请求体
            requests.post(
                ...,
                json={'user':'alex','pwd':'123'}
            )
            
            GET /index http1.1\r\nhost:c1.com\r\nContent-Type:application/json\r\n\r\n{"user":"alex","pwd":123}
    2.7 代理 proxies
        # 无验证
            proxie_dict = {
                "http": "61.172.249.96:80",
                "https": "http://61.185.219.126:3128",
            }
            ret = requests.get("https://www.proxy360.cn/Proxy", proxies=proxie_dict)
            
        
        # 验证代理
            from requests.auth import HTTPProxyAuth
            
            proxyDict = {
                'http': '77.75.105.165',
                'https': '77.75.106.165'
            }
            auth = HTTPProxyAuth('用户名', '密码')
            
            r = requests.get("http://www.google.com",data={'xxx':'ffff'} proxies=proxyDict, auth=auth)
            print(r.text)
    #----------------------------------------以下是不太常用的（了解）-------------------------------------------------
    2.8 文件上传 files
        # 发送文件
            file_dict = {
                'f1': open('xxxx.log', 'rb')  #本地问文件
            }
            requests.request(
                method='POST',
                url='http://127.0.0.1:8000/test/',
                files=file_dict
            )
            
    2.9 认证 auth
    
        内部：
            用户名和密码，用户和密码加密，放在请求头中传给后台。
            
                - "用户:密码"
                - base64("用户:密码")                            #加密
                - "Basic base64("用户:密码")"                    #构造字符串
                - 请求头：
                    Authorization： "Basic base64("用户|密码")"  #把构造的字符串放入请求头中
            
        from requests.auth import HTTPBasicAuth, HTTPDigestAuth

        ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))
        #执行HTTPBasicAuth时会调用__call__方法，然后走上面的流程
        print(ret.text)
        
    2.10 超时 timeout 
        # ret = requests.get('http://google.com/', timeout=1)
        # print(ret)
    
        # ret = requests.get('http://google.com/', timeout=(5, 1))
        # print(ret)
        
    2.11 允许重定向  allow_redirects
        ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
        print(ret.text)
        
    2.12 大文件下载 stream
        from contextlib import closing
        with closing(requests.get('http://httpbin.org/get', stream=True)) as r1:
        # 在此处理响应。
        for i in r1.iter_content():
            print(i)
#---------------------------下面的暂时用不到，知道就行---------------------------------------------          
    2.13 证书 cert
        - 百度、腾讯 => 不用携带证书（系统帮你做了）
        - 自定义证书
            requests.get('http://127.0.0.1:8000/test/', cert="xxxx/xxx/xxx.pem")
            requests.get('http://127.0.0.1:8000/test/', cert=("xxxx/xxx/xxx.pem","xxx.xxx.xx.key"))
    2.14 确认 verify =False 
"""


requests.get('http://127.0.0.1:8000/test/', cert="xxxx/xxx/xxx.pem")

requests中的session:

- session（推荐自己携带cookie）
以前的cookie是我们自己携带的，每次请求都需要携带，在requests模块中有一个叫session的东西
在seesion的内部会把我们访问的cookie全都保存下来，也会把header保存下来，也就是会把响应头和请求头全都保存下来，
我们在发请求的时候就不需要自己携带cookie了，它的内部会自动帮我们带上。
用法如下：    

    session = requests.Session()
    
    session.get()
    session.post()

示例：

# ######################爬取汽车之家#####################################

'''
import requests
#import requests:伪造浏览器发起Http请求

from bs4 import BeautifulSoup
# pip3 install BeautifulSoup4
# BeautifulSoup  将html格式的字符串解析成对象。         对象.find/find_all

response = requests.get("https://www.autohome.com.cn/news/")
response.encoding = 'gbk'
#传输之间默认用的是字节，把字节转化为字符串，指定字符编码

soup = BeautifulSoup(response.text,'html.parser') #把html格式的字符串解析成soup对象

div = soup.find(name='div',attrs={'id':'auto-channel-lazyload-article'})  #find找到是匹配成功的第一个数据

li_list = div.find_all(name='li') #找到div标签下的所有li

for li in li_list:

    title = li.find(name='h3')
    if not title:
        continue
    p = li.find(name='p')
    a = li.find(name='a')

    print(title.text)           #找h3标签对象里面的文本内容    标题
    print(a.attrs.get('href'))  #找a标签对象里面的属性      链接
    print(p.text)               #找p标签对象里面的文本内容      简介

    img = li.find(name='img')
    src = img.get('src')
    src = "https:" + src
    print(src)

    # 再次发起请求，下载图片
    file_name = src.rsplit('/',maxsplit=1)[1] #拿到文件名
    ret = requests.get(src)
    with open(file_name,'wb') as f:
        f.write(ret.content)   # .content是返回的二进制

'''

# ################################### 示例一：爬取数据（携带请起头） ###################################

"""
import requests
from bs4 import BeautifulSoup

r1 = requests.get(
    url='https://dig.chouti.com/',
    headers={
        'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
)

soup = BeautifulSoup(r1.text,'html.parser')

# 标签对象
content_list = soup.find(name='div',id='content-list')
# print(content_list)
# [标签对象,标签对象]
item_list = content_list.find_all(name='div',attrs={'class':'item'})
for item in item_list:
    a = item.find(name='a',attrs={'class':'show-content color-chag'})
    print(a.text.strip())
    # print(a.text)
"""


# ################################### 示例二：点赞 ###################################
#访问网站页面时会返回一个cookie，当登陆的时候会携带这个cookie(登陆时返回给我们的cookie是假的)

import requests
# 1. 查看首页
r1 = requests.get(
    url='https://dig.chouti.com/',
    headers={
        'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
)

# 2. 提交用户名和密码
r2 = requests.post(
    url='https://dig.chouti.com/login',
    headers={
        'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    },
    data={
        'phone':'8613121758648',
        'password':'woshiniba',
        'oneMonth':1
    },
    cookies=r1.cookies.get_dict()
)


# 3. 点赞
r3 = requests.post(
    url='https://dig.chouti.com/link/vote?linksId=20435396',
    headers={
        'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    },
    cookies=r1.cookies.get_dict()
)
print(r3.text)

""""""
# ################################### 示例三：自动登录GitHub ###################################
# 1. GET，访问登录页面
"""
- 去HTML中找隐藏的Input标签获取csrf token
- 获取cookie
"""

# 2. POST，用户名和密码
"""
- 发送数据：
    - csrf
    - 用户名
    - 密码
- 携带cookie
"""

# 3. GET,访问https://github.com/settings/emails
"""
- 携带 cookie
"""

import requests
from bs4 import BeautifulSoup

# ############## 方式一 ##############
#
# # 1. 访问登陆页面，获取 authenticity_token
# i1 = requests.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 携带authenticity_token和用户名密码等信息，发送用户验证
# form_data = {
# "authenticity_token": authenticity_token,
#     "utf8": "",
#     "commit": "Sign in",
#     "login": "wupeiqi@live.com",
#     'password': 'xxoo'
# }
#
# i2 = requests.post('https://github.com/session', data=form_data, cookies=c1)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = requests.get('https://github.com/settings/repositories', cookies=c1)
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
#     if isinstance(child, Tag):
#         project_tag = child.find(name='a', class_='mr-1')
#         size_tag = child.find(name='small')
#         temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
#         print(temp)


# ############## 方式二 ##############
# session = requests.Session()
# # 1. 访问登陆页面，获取 authenticity_token
# i1 = session.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 携带authenticity_token和用户名密码等信息，发送用户验证
# form_data = {
#     "authenticity_token": authenticity_token,
#     "utf8": "",
#     "commit": "Sign in",
#     "login": "wupeiqi@live.com",
#     'password': 'xxoo'
# }
#
# i2 = session.post('https://github.com/session', data=form_data)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = session.get('https://github.com/settings/repositories')
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
#     if isinstance(child, Tag):
#         project_tag = child.find(name='a', class_='mr-1')
#         size_tag = child.find(name='small')
#         temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
#         print(temp)

 拉勾网示例：

########################拉勾网###############################

'''
- 密码加密
    - 找js，通过python实现加密方式
    - 找密文，密码<=>密文

- Referer头， 上一次请求地址，可以用于做防盗链。

'''

import re
import requests

r1 = requests.get(
    url='https://passport.lagou.com/login/login.html',
    headers={
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
    }
)
X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0]
X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0]
# print(X_Anti_Forge_Token, X_Anti_Forge_Code)
# print(r1.text)
#
r2 = requests.post(
    url='https://passport.lagou.com/login/login.json',
    headers={
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
        'X-Anit-Forge-Code':X_Anti_Forge_Code,
        'X-Anit-Forge-Token':X_Anti_Forge_Token,
        'Referer': 'https://passport.lagou.com/login/login.html', # 上一次请求地址是什么？
    },
    data={
        "isValidate": True,
        'username': '15269853268',
        'password': 'ab18d328d7126ea65915c50359c22c0d',
        'request_form_verifyCode': '',
        'submit': ''
    },
    cookies=r1.cookies.get_dict()
)
print(r2.text)

小节：

请求头：
    user-agent
    referer
    host
    cookie
    特殊请起头，查看上一次请求获取内容。
        'X-Anit-Forge-Code':...
        'X-Anit-Forge-Token':...
请求体：
    - 原始数据
    - 原始数据 + token
    - 密文
        - 找算法 
        - 使用密文
        
套路：
    - post登录获取cookie，以后携带cookie 
    - get获取未授权cookie，post登录携带cookie去授权，以后携带cookie