'''
爬校花网视频：
一、请求rul
http://www.xiaohaur.com/v/
二、请求方式
    get
三、请求头信息
user-agent:用户代理
'''

 1 import time
 2 import requests
 3 #爬虫三部曲
 4 #1.发送请求
 5 def get_page(url):
 6     response = requests.get(url)
 7     return response
 8 # 2.解析数据
 9 import re
10 def parse_index(html):
11     # findall匹配所有
12     # re.findall('正则匹配规则','匹配文本','匹配模式')
13     # re.S:对所有文本进行搜索匹配
14     detail_urls = re.findall(
15         '<div class="items"><a class="imglink" href="(.*?)"',
16         html,re.S
17     )
18     return detail_urls
19 # 解析详情页
20 def parse_detail(html):
21     movie_url = re.findall('<source src="(.*?)">',html,re.S)
22     #print(movie_url)
23     if movie_url:
24         return movie_url[0]
25 # 3.保存数据
26 import uuid
27 #uuid.uuid4()根据时间戳生成一段世界上唯一的字符串
28 def save_video(content):
29     with open(f'{uuid.uuid4()}.mp4','wb')as f:
30         f.write(content)
31         print('视频下载完毕')
32 # main + 回车键
33 # 测试用例
34 if __name__ == '__main__':
35     for line in range(6):
36         url=f'http://www.xiaohuar.com/list-3-{line}.html'
37         #发送请求
38         response = requests.get(url)
39         #print(response)
40         # # 返回响应状态码
41         # print(response.status_code)
42         # # 返回响应文本
43         # print(response.text)
44 
45         #解析主页页面
46         detail_urls = parse_index(response.text)
47 
48         #循环遍历详情页url
49         for detail_url in detail_urls:
50             # print(detail_url)
51             # 往每一个详情页发送请求
52             detail_res = get_page(detail_url)
53             #print(response.text)
54             #解析详情页获取视频url
55             movie_url = parse_detail(detail_res.text)
56             # 判断视频url存在则打印
57             if movie_url:
58                 print(movie_url)
59 
60                 # 往视频url发送请求获取视频二进制流
61                 movie_res = get_page(movie_url)
62 
63                 # 把视频的二进制流传给save_video函数保存到本地
64                 save_video(movie_res.content)

'''
POST请求自动登录GitHub：
   一、请求rul
       https://github.com/session
   二、请求方式
        POST
   三.请求头
       cookies
        User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36
   四.请求体
      from data
      commit: Sign in
      utf8: ✓
      authenticity_token: LVyIb9FUxiI6XMain4PXzgOjKn9DzYzqdCwMvosVn+/Cht8LVgCuKjc7fbNfk5TiXf4W+6y56GmRnu1A4T0VIQ==
      login: sjdkjw
      password: 1562132
      webauthn-support: supported
'''

#获取token随机字符串
'''
1.访问登录页面获取token随机字符串
   一、请求rul
       https://github.com/login
   二、请求方式
        GET
   三.请求头
        cookies
        User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36
2.解析并提取token字符串
#正则
    <input type="hidden" name="authenticity_token" value="(.*?)" />
'''
import requests
import re
login_url ='https://github.com/login'
#login页面的请求头信息
login_header = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}
login_res = requests.get(url=login_url,headers=login_header)
#print(login_res.text)
#解析提取token字符串
authenicity_token = re.findall(
    '<input type="hidden" name="authenticity_token" value="(.*?)" />',
    login_res.text,re.S
)[0]
print(authenicity_token)

# 2.开始登录github
'''
POST请求自动登录GitHub：
   一、请求rul
       https://github.com/session
   二、请求方式
        POST
   三.请求头
        cookies
        User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36
   四.请求体
    from data
      commit: Sign in
      utf8: ✓
      authenticity_token: LVyIb9FUxiI6XMain4PXzgOjKn9DzYzqdCwMvosVn+/Cht8LVgCuKjc7fbNfk5TiXf4W+6y56GmRnu1A4T0VIQ==
      login: ****
      password: *****
      webauthn-support: supported
'''
#获取login页面的cookies信息
login_cookies = login_res.cookies.get_dict()
# session登录url
session_url = 'https://github.com/session'

#请求头信息
session_headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}

#请求体信息
form_data = {
    "commit": "Sign in",
    "utf8": "✓",
    "authenticity_token": "authenicity_token",
    "login": "****",
    "password": "*****",
    "webauthn-support": "supported"
}
session_res = requests.post(url=session_url,
                            headers=session_headers,
                            cookies=login_cookies,
                            data=form_data
                            )
with open('github1.html','w',encoding='utf-8') as f:
    f.write(session_res.text)