批量爬取抖音视频

1.先创建dou_url.txt,其实不用创建也行，运行第一遍代码的时候程序会自动创建

2.dou_url.txt里面可以填写多个视频url即可爬取，也可以填url加文字，因为用了正则表达式匹配。。。

3.比如：7.12 oQK:/ 重生回来第一节课，就给老师上了一课%%漫画解说 %%漫画 %%二次元 https://v.douyin.com/LK9nmKp/ 复制此链接，打开Dou音搜索，直接观看视频！

4.其实原理就是正则表达式匹配url

5.用的是selenium框架，鄙人才疏学浅，滑动验证码实在是不会搞，( ╯-_-)╯┴—┴

import time
import requests
import re
from selenium.webdriver import Chrome
import os
 
 
def create_note():
    if os.path.exists('dou_url.txt') == False:
        open('dou_url.txt', mode='w')
        print('创建 dou_url.txt 成功')
        print('请在 dou_url.txt 输入内容')
        return False
    else:
        print('dou_url.txt 已存在')
        return True
 
 
def read_txt():
    with open('dou_url.txt', 'r', encoding=u'utf-8') as f:
        data = f.read()  # 读取文件
        pattern = re.compile('[a-zA-z]+://[^\s]*')
        url = pattern.findall(data)
        print(url)
        return url
 
 
def open_url(url):
    web.get(url)
    time.sleep(2)
    try:
        while web.find_element_by_xpath('//*[@id="captcha-verify-image"]') is not None:
            print(end='')
    except:
        print(end='')
 
    time.sleep(1)
 
    source = web.page_source
 
    r = re.compile(r'<source class="" src="(.*?)" type="">')
    res = r.findall(source)
    res_url = 'https:' + res[0]
    print(res_url)
    return res_url
 
 
def download_video():
    url = read_txt()
    path = 'douyin'
    if not os.path.exists(path):
        os.mkdir(path)
 
    for i in url:
        video_url = open_url(i)
 
        with open(path + '\\' + f"{i.split('/')[-2]}" + '.mp4', 'wb') as f:
            f.write(requests.get(video_url).content)
    f.close()
 
 
if __name__ == '__main__':
    if create_note() == True:
        web = Chrome()
        download_video()