15-bs4-爬取图片实战

https://m.ivsky.com/

# 1、拿到主页面的源代码，然后提取到子页面的链接地址，href
# 2、通过href拿到子页面的内容，从子页面中找到图片的下载地址img -> src
# 3、下载图片

import requests
from bs4 import BeautifulSoup
import time

url = "https://www.ivsky.com/"

headers = {
    "user-agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.55 Mobile Safari/537.36 Edg/96.0.1054.43"
}

resp = requests.get(url, headers=headers)
resp.encoding = "utf-8"

# 把页面源代码交给BeautifulSoup管理，产生bs4对象
main_page = BeautifulSoup(resp.text, "html.parser")

ileft = main_page.find("div", attrs={"id": "sy_load"})
uls = ileft.find_all("ul")

for ul in uls:
    lis = ul.find_all("li")
    for li in lis:
        div = li.find("div")
        a = div.find("a")
        child_url = url + a.get("href")   # 通过get可以获得标签的属性值
        resp1 = requests.get(child_url, headers=headers)
        resp1.encoding = "utf-8"
        # 将子页面的源代码交给bs4管理
        child_page = BeautifulSoup(resp1.text, "html.parser")
        # print(child_page)
        ul = child_page.find("ul", attrs={"class": "ul_third"})
        # print(len(ul))
        lis = ul.find_all("li")
        for li in lis:
            img = li.find("img")
            src = img.get("src")  # 获取到每一个图片的路径

            # print(src)

            img_name = src.split("/")[-1]  # 我们要保存的图片的名字

            # 下载图片
            img_resp = requests.get("https:" + src)
            with open("img/"+img_name, mode="wb") as f:
                f.write(img_resp.content)   # 这里img_resp.content拿到的是字节
            time.sleep(1)
            print(img_name)