python利用urllib和xpath爬取并保存图片

概要

在网络时代，图片是信息传递的重要形式之一，而Python作为一种多用途的编程语言，可以用来编写爬虫从网页上获取图片，并保存到本地。本文将介绍如何使用Python爬虫实现这一功能，并探讨一些进阶技巧。

实现

（1）请求对象定制

# 请求对象定制
def create_request(page):

    if 1 == page:
        url = 'https://sc.chinaz.com/tupian/huacaotupian.html'
    else:
        url = 'https://sc.chinaz.com/tupian/huacaotupian_' + str(page) + '.html'

    # 防止UA（User-Agent）检查
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'
    }

    request = urllib.request.Request(url=url, headers=headers)
    return request

（2）获取网页源码

# 获取网络源码
def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

(3)解析并下载图片

# 下载
def down_load(content):
    tree = etree.HTML(content)
    name_list = tree.xpath('//div[@class="container"]//div/div/img/@alt')
    img_list = tree.xpath('//div[@class="container"]//div/div/img/@data-original')
    # for i in range(len(name_list)):
    #     print('name', i)
    # for i in range(len(img_list)):
    #     print('src', i)
    for i in range(len(name_list)):
        urllib.request.urlretrieve(url= 'https:' + img_list[i], filename='./out_Data/img/' + name_list[i] + '.png')

解析网页源码这里用到了xpath，xpath是lxml下的一个包，使用时，需要导入：

from lxml import etree

完整代码

完整代码如下：

import urllib.request
from lxml import etree

# 分析页码之间的关系
# get请求
# https://sc.chinaz.com/tupian/huacaotupian.html  1
# https://sc.chinaz.com/tupian/huacaotupian_2.html 2
# https://sc.chinaz.com/tupian/huacaotupian_3.html  3
# https://sc.chinaz.com/tupian/huacaotupian_4.html  4

# 请求对象定制
def create_request(page):

    if 1 == page:
        url = 'https://sc.chinaz.com/tupian/huacaotupian.html'
    else:
        url = 'https://sc.chinaz.com/tupian/huacaotupian_' + str(page) + '.html'

    # 防止UA（User-Agent）检查
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'
    }

    request = urllib.request.Request(url=url, headers=headers)
    return request

# 获取网络源码
def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

# 下载
def down_load(content):
    tree = etree.HTML(content)
    name_list = tree.xpath('//div[@class="container"]//div/div/img/@alt')
    img_list = tree.xpath('//div[@class="container"]//div/div/img/@data-original')
    # for i in range(len(name_list)):
    #     print('name', i)
    # for i in range(len(img_list)):
    #     print('src', i)
    for i in range(len(name_list)):
        urllib.request.urlretrieve(url= 'https:' + img_list[i], filename='./out_Data/img/' + name_list[i] + '.png')



if __name__ == '__main__':
    start_page = int(input('请输入起始页码： '))
    end_page = int(input('请输入截止页码： '))
    for page in range(start_page, end_page + 1):
        print('下载至第' + page + '页')
        # 请求对象定制
        request = create_request(page)
        # 获取网页源码
        content = get_content(request)
        # 下载数据
        down_load(content)