python中的异常处理

在代码运行之中，经常会遇到代码出错然后整个代码停滞的问题，特别是爬取多个图片或视频的时候，他可能在其中某一个环节突然出错，然后整个代码就停止了爬取，所以我们需要采用异常处理的办法对异常部分处理并跳过。

# 异常处理
import os
while True:
    # 加入异常处理防止程序终止
    try:  # 程序正常运行时执行的语句
        file_name = input("输入要创建文件夹的名字：")
        os.mkdir(file_name)
    except:  # 程序异常时执行的语句
        print("文件夹已存在，无需再次处理")

这就是异常处理的基本格式，我们来尝试运行一下

这里我们可以看见，第一次代码正常运行，第二次出现了异常处理所显示的语句。

接下来，我们把它带入图片爬取项目之中

# 导入相应库
import requests
import re
import os

# 获取网络源代码
def get_html(url, headers, params):
    response = requests.get(url, headers=headers, params=params)
    # 设置源代码的编码方式
    response.encoding = "utf-8"
    # 利用循环判断网页是否能打开
    if response.status_code == 200:
        return response.text
    else:
        print("网址源码获取错误")

# 解析提取图片的源地址
def pares_pic_url(html):
    result = re.findall('thumbURL":"(.*?)"', html, re.S)
    return result

# 获取图片二进制源码
def get_pic_content(url):
    response = requests.get(url)
    return response.content

# 保存图片
def save_pic(fold_name,content,pic_name):
    with open(fold_name + "/" + str(pic_name)+".jpg","wb") as f:
        f.write(content)
        f.close()

# 定义一个文件夹保存
def create_fold(fold_name):
    # 异常处理
    try:
        os.mkdir(fold_name)
    except:
        print("文件夹已存在")
# 定义一个main函数调用get_html函数
def main():
    try:
        # 输入文件夹名字
        fold_name = input("请输入图片名:")
        # 输入你要抓取的数量
        page_num = input("请输入你要抓取的页数:")
        # 调用函数，创建文件夹
        create_fold(fold_name)
        # 定义图片名字
        pic_name = 0
        # 构建循环，控制页面
        for i in range(int(page_num)):
            try:
                url = "https://image.baidu.com/search/acjson?tn=resultjson_com&logid=10657561438670404501&ipn=rj&ct=201326592&is=&fp=result&fr=&word=%E5%A4%A7%E7%86%8A%E7%8C%AB&queryWord=%E5%A4%A7%E7%86%8A%E7%8C%AB&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=&copyright=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=1&expermode=&nojc=&isAsync=&pn=30&rn=30&gsm=1e&1695870456938="
                headers = {
                    "Accept": "text/plain, */*; q=0.01",
                    "Accept-Encoding": "gzip, deflate",
                    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
                    "Connection": "keep-alive",
                    "Cookie": 'BAIDUID=E9B7B77E6EFAEA9AE94B261906052872:FG=1; BIDUPSID=E9B7B77E6EFAEA9AE94B261906052872; PSTM=1695258294; BAIDUID_BFESS=E9B7B77E6EFAEA9AE94B261906052872:FG=1; BDUSS=hPdE9iMEdZdFoyUnAyaEJESFRKZy0xcmRXemRnazJrZTN3UmRsQmFnd1ZKVE5sRVFBQUFBJCQAAAAAAQAAAAEAAAA2tPJCAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABWYC2UVmAtlTW; BDUSS_BFESS=hPdE9iMEdZdFoyUnAyaEJESFRKZy0xcmRXemRnazJrZTN3UmRsQmFnd1ZKVE5sRVFBQUFBJCQAAAAAAQAAAAEAAAA2tPJCAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABWYC2UVmAtlTW; indexPageSugList=%5B%22csdn%22%5D; RT="z=1&dm=baidu.com&si=1a697eb9-7afe-4cf7-ad56-7d660c33216d&ss=lmyje565&sl=2&tt=5so&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=7r4&ul=cbp4&hd=cbqt"; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm',
                    "Host": "image.baidu.com",
                    "Referer": "https://image.baidu.com/search/index?tn=baiduimage&ps=1&ct=201326592&lm=-1&cl=2&nc=1&ie=utf-8&dyTabStr=MTEsMCwxLDYsMyw1LDQsMiw4LDcsOQ%3D%3D&word=%E5%A4%A7%E7%86%8A%E7%8C%AB",
                    "Sec-Ch-Ua": '"Microsoft Edge";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
                    "Sec-Ch-Ua-Mobile": "?0",
                    "Sec-Ch-Ua-Platform": '"Windows"',
                    "Sec-Fetch-Dest": "empty",
                    "Sec-Fetch-Mode": "cors",
                    "Sec-Fetch-Site": "same-origin",
                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36 Edg/117.0.2045.43",
                    "X-Requested-With": "XMLHttpRequest",
                }
                params = {
                    "tn": "resultjson_com",
                    "logid": "10657561438670404501",
                    "ipn": "rj",
                    "ct": "201326592",
                    "fp": "result",
                    "word": fold_name,
                    "queryWord": fold_name,
                    "cl":"2",
                    "lm":"-1",
                    "ie": "utf - 8",
                    "oe": "utf - 8",
                    "nc": "1",
                    "pn": str(int(i+1)*30),
                    "rn": "30",
                    "gsm": "1e",
                }
                html = get_html(url, headers, params)
                # print(html)
                result = pares_pic_url(html)
                # print(result)

                # 使用for循环遍历列表
                for item in result:
                    # print(item)
                    # 调用函数获取二进制源码
                    pic_content = get_pic_content(item)
                    save_pic(fold_name, pic_content, pic_name)
                    pic_name += 1
                    print("正在保存第 " + str(pic_name))
            except:
                print("抓取第 "+str(i)+" 页错误")
    except:
        print("数据获取异常")


# 执行main函数
if __name__ == '__main__':
    main()

紧接着，我们来运行他

可以看到，项目正在正常运行，并未出现报错，但是在异常地方进行了提示。