python爬虫练习——下载梨视频，带进度条

main.py

import requests
import random
import lib.tools as t
import os

def main():
    try:
        input_url = input("请输入视频页网址：")
        contId = input_url.split("_")[1]
        mrd = random.randint(10,99)/random.randint(100,999)
        get_url = f"https://www.pearvideo.com/videoStatus.jsp?contId={contId}&mrd={mrd}"
        header = {
            "Referer":f"https://www.pearvideo.com/video_{contId}"
        }
        r = requests.get(get_url,headers=header)
        srcUrl = r.json()["videoInfo"]["videos"]["srcUrl"]
        systemTime = r.json()["systemTime"]
        srcUrl = srcUrl.replace(systemTime,f"cont-{contId}")
        file_name = contId + os.path.splitext(srcUrl)[-1] # 取扩展名拼接视频名
        print("下载开始:")
        t.download_file(srcUrl,file_name)
        print(f"{file_name}下载结束")
    except Exception:
        pass

if __name__ == "__main__":
    main()

tools.py

import requests
import os
import glob
import progressbar

# 取出中间文本
def getmidstring(html, start_str, end):
    start = html.find(start_str)
    if start >= 0:
        start += len(start_str)
        end = html.find(end, start)
        if end >= 0:
            return html[start:end].strip()

# 下载文件
def download(down_url,save_path):
    reponse = requests.get(down_url)
    with open(save_path,'wb') as f:
        f.write(reponse.content)

# 下载文件带进度条        
def download_file(url, path):
    with requests.get(url, stream=True) as r:
        chunk_size = 1024
        content_size = float(r.headers[ 'content-length' ])
        
        # 进度条样式
        widgets = [
           '下载: ', progressbar.Percentage(), # 进度条标题
           ' ', progressbar.Bar(marker='>', left='[', right=']', fill=' '), # 进度条填充、边缘字符
           ' ', progressbar.Timer(), # 已用的时间
           ' ', progressbar.ETA(), # 剩余时间
           ' ', progressbar.FileTransferSpeed(),# 下载速度
        ]
        
        bar = progressbar.ProgressBar(widgets=widgets, max_value=content_size) # 实例化对象

        with open(path, "wb") as f:

           loaded = 0
           bar.start() # 调用进度条start方法，在调用update方法
           for chunk in r.iter_content(chunk_size=chunk_size):
              loaded += len(chunk)
              bar.update(loaded) # 更新进度条状态
              f.write(chunk)
           bar.finish() # 结束进度条


# 读文件内容
def read_infotxt(file_name):
    f = open(file_name)    
    info = f.read()
    f.close()
    return info

# 把内容写入文本文件
def write_txt(file_name,txt_content):
    with open(file_name,"wb") as f:
        f.write(txt_content.encode("gbk"))

# 创建文件夹
# 遇到重复文件夹命名为文件夹目录_1(2,3,4……)
# 返回文件夹目录名称
def mkdir(path,root_flag=False):
    folder = os.path.exists(path)
    floder_path = path
    if not folder:
        os.makedirs(path)
    else:
        if not root_flag:
            num_p = 1
            sub_path = glob.glob(path + '*')
            if sub_path:
                # 最后一个创建目录
                last_path = sub_path[-1]
                floder_path = last_path + '_{}'.format(num_p)
                if last_path.find('_') > 0:
                    num_str = last_path.split('_')
                    if num_str[-1].isdigit():
                        num_p = int(num_str[-1]) + 1
                        floder_path = last_path[0:last_path.rfind(
                            '_')] + '_{}'.format(num_p)
                        os.makedirs(floder_path)
                    else:
                        os.makedirs(floder_path)
                else:
                    os.makedirs(floder_path)
    return floder_path

结果：