python3爬取echart图片

直接上代码：

# coding=utf-8

from urllib import request
from bs4 import BeautifulSoup
import requests
# import urllib
import os
import time
import chardet
import collections
# 目标地址
url="https://echarts.baidu.com/"
# 像目标URL发送get请求
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
chromHeaders={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.137 Safari/537.36 LBBROWSER'}
user_agents = [
    {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11'},
    {'User-Agent':'Opera/9.25 (Windows NT 5.1; U; en)'},
    {'User-Agent':'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)'},
    {'User-Agent':'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)'},
    {'User-Agent': 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12'},
    {'User-Agent': 'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9'},
    {'User-Agent':"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7"},
    {'User-Agent':"Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "},
]
req = request.Request(url=url, headers=headers) #防止浏览器拦截
#req = request.Request(url)
# 获取URL请求内容
response = request.urlopen(req)
# 读取返回的HTML内容
html = response.read()
chardit1 = chardet.detect(html) #获取文本编码
"""
if("gb2312"==chardit1['encoding'].lower()):
    print(html)
else:
    print(html.decode(chardit1['encoding']))
"""
fout =open("test2.html","wb")
fout.write(html)
fout.close()
# 解析HTML
soup = BeautifulSoup(html, 'html.parser')

# 使用find_all方法查找HTML中所有<img>标签
all_img = soup.find_all('img')
print("all_img:")
print(all_img)

# 遍历所有爬取到的<img>
for img in all_img:
    # 定义存储位置
    root = "D://download//d//"
    if("data-src" in str(img) or "src" in str(img)):
        if("data-src" in str(img)):
            scr = img['data-src']
        else:
            scr = img['src']
    else:
        continue

    # 获取遍历<img>得到的图片src地址
    img_url = scr
    print("img_url:")
    print(img_url)
    print("img:")
    print(img)
    # 拼接图片下载完整地址
    img_full_url = url + img_url
    print("img_full_url:")
    print(img_full_url)

    if ("alt" in str(img)):
        alt = img['alt']

    else:
        alt=str(time.time())
    print("alt:" + alt)
    """
    # 遍历获取图片名称
    for alt in all_img:
        print('alt = ', alt)
        
        img = collections.defaultdict(img)
        img.setdefault('alt','0');
        alt = img['alt']
        if(alt=='0'):
            alt=str(time.time());
    """
    # 定义图片存储名称和格式
    # path = root + img_full_url.split('/')[-1] + ".jpg"     # 使用完整下载地址最后分割部分作为图片名称
    suffix =img_url.split(".")[len(img_url.split("."))-1]
    list= ['jpg','jpeg','png','gif']
    if(suffix not in (list)):
        suffix="png"
    path = root + alt + "."+suffix #定义后缀

    try:
        # 判断路径是否存在
        if not os.path.exists(root):
            print('没有路径,请新建')
            os.mkdir(root)
        # 判断图片是否存在
        if not os.path.exists(path):
            print('文件夹没有该图片')
            if("http://" in img_url or  "https://" in img_url ):
                reqUrl=img_url
            else:
                reqUrl=img_full_url

            print("reqUrl:")
            print(reqUrl)
            r = requests.get(url=reqUrl, headers=user_agents[7])
            # 检查请求是否成功
            r.raise_for_status()
            # wb表示写入二进制文件，使用r.content方式响应二进制内容
            with open(path, "wb") as f:
                f.write(r.content)
            print('爬取完成\n\n')
        else:
            print('图片已经存在')
    except Exception as e:
        print('爬取失败：' + str(e))
        continue

代码完成 关于引入的第三方库 

在

在python安装路径的scripts路径下敲这个命令 pip install beautifulsoup4  

成功安装的话如下

其他的第三方库类似

代码参考来自https://blog.csdn.net/yihongyuantufei/article/details/81745565

在其基础上进行修改，主要增加了1.浏览器拦截2.自动获取后缀问题3.获取网站的编码格式4.图片请求路径的优化等