pip3 install requests

import requests

def get_page(url):response = requests.get(url)return response

import re
def parse_index(html):# findall匹配所有# re.findall（'正则匹配规则'，'匹配文本'.'匹配模式')# re.S:对全部文本进行搜索匹配detail_urls = re.findall('<div class="items"><a class="imglink" href="(.*?)"', html, re.S)return detail_urls# 解析详情页
def parse_detail(html):movie_url = re.findall('<source src="(.*?)">', html, re.S)if movie_url:return movie_url[0]

import uuid
def save_video(content):with open(f'{uuid.uuid4()}.mp4','wb') as f:f.write(content)print('视频下载完毕...请客人观赏!!!')

import requests# 1 发送请求
def get_page(url):response = requests.get(url)return response# 2 解析数据
import re
def parse_index(html):# findall匹配所有# re.findall（'正则匹配规则'，'匹配文本'.'匹配模式')# re.S:对全部文本进行搜索匹配detail_urls = re.findall('<div class="items"><a class="imglink" href="(.*?)"', html, re.S)return detail_urls
# 解析详情页
def parse_detail(html):movie_url = re.findall('<source src="(.*?)">', html, re.S)if movie_url:return movie_url[0]# 3 保存数据
import uuid
def save_video(content):with open(f'{uuid.uuid4()}.mp4','wb') as f:f.write(content)print('视频下载完毕...请客人观赏!!!')# 测试用例
if __name__ == '__main__':for line in range(6):url = f'http://www.xiaohuar.com/list-3-{line}.html'# 发送请求response = get_page(url)# 解析主页页面detail_urls = parse_index(response.text)# 循环遍历详情页urlfor detail_urls in detail_urls:# 往每一个详情页发送请求detail_res = get_page(detail_urls)# 解析详情页获取视频urlmovie_url = parse_detail(detail_res.text)# 判断视频url存在则打印if movie_url:print(movie_url)# 往视频url发送请求获取视频二进制流movie_res = get_page(movie_url)# 把视频的二进制流传给save_video函数去保存到本地save_video(movie_res.content)

import requests
import re
login_url = 'https://github.com/login'
login_header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}
login_res = requests.get(url=login_url, headers=login_header)# 解析提取token字符串
authenticity_token = re.findall('<input type="hidden" name="authenticity_token" value="(.*?)"',login_res.text,re.S
)[0]
print(authenticity_token)# 获取login页面的cookies信息
login_cookies = login_res.cookies.get_dict()

# 请求url
session_url = 'https://github.com/session'
# 请求头信息
session_headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) 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": authenticity_token,"login": "*******","password": "********","webauthn-support": "supported"
}session_res = requests.post(url=session_url,headers=session_headers,cookies=login_cookies,data=form_data
)with open('github.html', 'w', encoding='utf-8') as f:f.write(session_res.text)

import requests
import re
login_url = 'https://github.com/login'
login_header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}
login_res = requests.get(url=login_url, headers=login_header)# 解析提取token字符串
authenticity_token = re.findall('<input type="hidden" name="authenticity_token" value="(.*?)"',login_res.text,re.S
)[0]
print(authenticity_token)# 获取login页面的cookies信息
login_cookies = login_res.cookies.get_dict()# 请求url
session_url = 'https://github.com/session'# 请求头信息
session_headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) 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": authenticity_token,"login": "*******","password": "*******","webauthn-support": "supported"
}session_res = requests.post(url=session_url,headers=session_headers,cookies=login_cookies,data=form_data
)with open('github.html', 'w', encoding='utf-8') as f:f.write(session_res.text)