网站爬取分析流程

抽屉网的爬取过程分析
# ################################### 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 ###################################
"""
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)

爬取github的分析流程
""""""
# ################################### 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)

爬取拉钩网的流程分析
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': '15131255089',
        'password': 'ab18d270d7126ea65915c50288c22c0d',
        'request_form_verifyCode': '',
        'submit': ''
    },
    cookies=r1.cookies.get_dict()
)
print(r2.text)