利用python爬取qq个性网图片

利用python爬取qq个性网图片

网站头像布局大同小异，稍改代码即可爬取想要的头像。
不多bb，上代码。

import requests
from parsel import Selector
import time


# 返回处理好的链接地址
def get_url():

    url_list = []
    # 循环拼接链接地址
    for url_index in range(1, 11, 1):
        if url_index == 1:
            url = 'https://www.woyaogexing.com/touxiang/z/ktnan/index.html'
            url_list.append(url)
        else:
            url = 'https://www.woyaogexing.com/touxiang/z/ktnan/index' + '_' + f'{url_index}' '.html'
            url_list.append(url)
    return url_list


# 获取每个链接的html，并提取每个类图片地址
def get_img_html():

    url_list = get_url()
    url_lists = []
    count = 0
    for html_url in url_list:
        response = requests.get(html_url)
        response.encoding = 'utf-8'
        html = response.text
        # 创建对象，解析图片，提取地址
        selector = Selector(text=html)
        selectors = selector.xpath("//div[@class='pMain']")
        left_url = selectors.xpath("./div[@class='txList ']/a/@href").getall()
        right_url = selectors.xpath("./div[@class='txList listRight']/a/@href").getall()
        url_all = left_url + right_url
        url_lists.append(url_all)
        count += 1
        print(f'第{count}页成功爬取url,正在放入列表,休息3s--->')
        time.sleep(3)
    print('-->爬取url完成')
    # 用set集合去重，防止有相同链接
    url_sets = set()
    for url_list in url_lists:
        for url_url in url_list:
            url_sets.add(url_url)
    return url_sets


# 获取单张小图片的地址，并返回链接地址列表
def get_img_url():

    url_sets = get_img_html()
    url_lists = []
    count = 0
    img_real = []
    for url in url_sets:
        # 拼接每个小图片的地址
        http_url = 'https://www.woyaogexing.com' + url
        response = requests.get(http_url)
        response.encoding = 'utf-8'
        selector = Selector(text=response.text)
        # 解析图片
        selectors = selector.xpath("//ul[@class='artCont cl']")
        img_url = selectors.xpath("./li[@class='tx-img']/a/@href").getall()
        url_lists.append(img_url)
        count += 1
        print(f'解析第{count}页url-->')
    print('解析url完成-->')
    for url_list in url_lists:
        for url in url_list:
            img_real.append(url)
    return img_real


# 下载图片到指定路径
def download_pic():
    img_urls = get_img_url()
    http = 'https:'
    count = 0
    for img_url in img_urls:
        # 拼接图片地址
        real_url = http + img_url
        print(real_url)
        response = requests.get(real_url)
        count += 1
        # 下载图片到本地
        with open(f'.//pic/ {count}.jpeg', 'wb') as f:
            f.write(response.content)
            print('第%s张照片成功下载照片到指定路径' % count)
    f.close()


if __name__ == '__main__':

    download_pic()

爬取结果

欢迎各位大神交流。