通过爬虫爬取一些图片

def main_page():#定义一个函数
    with open("childPage.txt",mode="w") as f:#创建一个名为childPage.txt的文件
        for i in range(1,56):#规定爬取数量
            try:
                resp = requests.get(f"https://www.umei.cc/bizhitupian/we
imeibizhi/{i}.htm")
                # <meta http-equiv="Content-Type"
content="text/html; charset=utf-8" />
                resp.encoding = 'utf-8' # 处理中
⽂乱码, 这⾥要和⻚⾯上的charset对应
                main_page = BeautifulSoup(resp.text, "html.parser")
                typeListDiv =
                main_page.find("div", attrs={"class":"TypeList"})
                main_a_list =typeListDiv.find_all("a")
                for main_a in main_a_list:
                href = main_a.get("href") #拿到某⼀个标签中xxx属性的值
                f.write(href)
                f.write("\n")
 print(f"https://www.umei.cc/bizhitupian/weimeibizhi/{i}.htm, 成功了!")
            time.sleep(0.5)
            except:
 
 print(f"https://www.umei.cc/bizhitupian/weimeibizhi/{i}.htm, 出错了")
            print(resp.text)
            break # 也可以记录下来, 供以后查错

def child_page():
    with open("childPage.txt", mode="r") as
f:
    for line in f:
    line = line.strip()
    resp = requests.get(line)
    resp.encoding='utf-8'
    child = BeautifulSoup(resp.text,"html.parser")
    div = child.find("div",
class_="ImageBody")
    img = div.find("img")
    if img:
        src = img.get("src")
        print(src)
    else:
        print(line, "没有图⽚")

def download_img(src):
    with open("img/"+src.split("/")[-1],mode="wb") as f:
    resp = requests.get(src) # 下载图⽚
    f.write(resp.content) # 图⽚写⼊⽂件
    print(src, "down!"）