python爬虫-80电子书，爬图片

'''
作者：Caric_lee
日期：2018
查看图片
'''
import requests
from bs4 import BeautifulSoup
r = requests.get("http://www.80txt.com/sort3/1.html")
m = r.content.decode("utf-8")

tupian = BeautifulSoup(m, "html.parser")
all = tupian.find_all("img")
print(all)
# for i in all:
#     print(i.a.img)   # 取 照片

# 循环把照片连接放到list里面
# tupian1 = BeautifulSoup(m, "html.parser")
# all1 = tupian1.find_all("img")
# image = []
# for j in all1:
#     print(j["src"])
#     image.append(j["src"])
# print(image)

# 把照片连接存储在文件上
for i in all:
    try:
        url = i["src"]
        print(url)
        name = i["title"]
        print(name)
        r1 = requests.get(url)
        path ="D:\\test"

        # 判断是否存着这个目录
        import os
        if not os.path.exists(path):
            os.mkdir()
        fp = open(path + "\\%s.jpg" % name, "wb")
        fp.write(r1.content)  # r1.content获取的是二进制流
        fp.close()
    except Exception as msg:
        print(msg)

 

转载于:https://www.cnblogs.com/lixy-88428977/p/9366856.html