Python爬虫---使用BeautifulSoup下载麦当劳点餐图片

velpro_!2024-01-02 15:08

步骤：

导入需要使用的包
定位正确的url地址
发请求
获取响应
解析响应的内容
将获取的xpath语法转换成bs4语法

7.下载图片

python 复制代码

import urllib.request
from bs4 import BeautifulSoup

# url
url = "https://www.mcdonalds.com.cn/index/Food/menu/burger"

# 请求
response = urllib.request.urlopen(url=url)

# 响应
content = response.read().decode("utf-8")
# print(content)

# 解析
soup = BeautifulSoup(content, "lxml")

# img_list = "//div[@class="pic"]/img/@src"    # xpath语法
# name_list = "//div[@class="col-md-3 col-sm-4 col-xs-6"]//span/text()"   # xpath语法

name_list = soup.select("div[class='col-md-3 col-sm-4 col-xs-6'] span")  # BeautifulSoup语法
img_list = soup.select(".pic>img")
# print(type(name_list))
# print(name_list, len(name_list))
# print(img_list)

# for name in name_list:
#     print(name.get_text())  # 每个名字
#     print(name.string)  # 每个名字
#     print(name_list.index(name))  # 每个名字的索引

for img in img_list:
    # print(img["src"])  # 每张图片的地址
    img_src = img["src"]
    # print(img_list.index(img))   # 每个图片的索引
    # name = img_src.split("/")[-1]  # 图片命名
    name = name_list[img_list.index(img)].get_text()  # 图片命名
    urllib.request.urlretrieve(url=img_src, filename="./image/1/" + name + ".jpg")  # 下载图片
    print(f"图片{name}下载了")