""""""

# ################################### 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‘)
content_list = soup.find(name=‘div‘,attrs={"id":"content-list"})
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())

"""
# ################################### 示例二：登陆点赞 ###################################
"""
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() 
    # 套路 正常用户必然会先访问首页然后再登陆
    # 如果你直接登陆必然是爬虫，因此设计在第一次访问首页的时候先创建cookie 并且返回了回去
    # 并且要求你第二次访问的时候要带着这个 cookie 
)

# 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)
"""

# ############## 方式二 session 方式 ##############
"""
# 用 session 自动封装好 cookie 不用在以后自己携带
import requests

session = requests.Session()
i1 = session.get(url="http://dig.chouti.com/help/service")
i2 = session.post(
    url="http://dig.chouti.com/login",
    data={
        ‘phone‘: "8615131255089",
        ‘password‘: "xxooxxoo",
        ‘oneMonth‘: ""
    }
)
i3 = session.post(
    url="http://dig.chouti.com/link/vote?linksId=8589523"
)
print(i3.text)
"""

import re
import requests


"""
密码加密了的时候
    找js 通过 python 实现加密方式
    直接把加密后的密文拿来用
"""

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‘,
    }
)

"""
    有两个奇怪的东西，是网站的防御机制
        这两个数据必然是对方发给我们的
        要不在响应头里面，要不在响应体里面
            响应头看不到。那就去响应体里面找。
"""

# 因为不是写在标签里面的。只能用正则来拿了
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)

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？很多网站会要求带着个才可以继续
    },
    data={
        "isValidate": True,
        ‘username‘: ‘15131255089‘,
        ‘password‘: ‘ab18d270d7126ea65915c50288c22c0d‘,    # 直接发密文了
        ‘request_form_verifyCode‘: ‘‘,
        ‘submit‘: ‘‘
    },
    cookies=r1.cookies.get_dict()
)
print(r2.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

# ##########################################################

#  访问登陆页面，获取 authenticity_token
i1 = requests.get(
    url=‘https://github.com/login‘
    )
soup1 = BeautifulSoup(i1.text, features=‘lxml‘)
tag = soup1.find(name=‘input‘, attrs={‘name‘: ‘authenticity_token‘})
authenticity_token = tag.get(‘value‘) # authenticity_token 拿到
c1 = i1.cookies.get_dict()
i1.close()

#  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, # 放在请求体中发过去
    "utf8": "",
    "commit": "Sign in",
    "login": "",
    ‘password‘: ‘‘
}

i2 = requests.post(
    url=‘https://github.com/session‘, 
    data=form_data, 
    cookies=c1
    )
c2 = i2.cookies.get_dict()
c1.update(c2) # 将两次的 cookie 整合一起
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)

user-agent
referer
host
cookie

‘X-Anit-Forge-Code‘:...
‘X-Anit-Forge-Token‘:...

- 原始数据
- 原始数据 + token
- 密文
　　- 找算法 
　　- 使用密文

- 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