爬取站长素才图片

1.查找网页的接口

1.使用谷歌浏览器，右击检查，点击“Network”，查找资源路径

	第一页的数据：http://sc.chinaz.com/tag_tupian/OuMeiMeiNv.html

​	第二页的数据:   http://sc.chinaz.com/tag_tupian/OuMeiMeiNv_2.html

​	第三页的数据：http://sc.chinaz.com/tag_tupian/OuMeiMeiNv_3.html

2.找出资源路径的规律

import urllib.request

def create_request(page):
    base_url = 'http://sc.chinaz.com/tag_tupian/OuMeiMeiNv'
    #第一页
    if page == 1:
        url = base_url + '.html'
    #第一页之后的
    else:
        url = base_url + '_' + str(page) + '.html'

     #定制请求头，绕过网站的反爬手段   
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }

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

2.使用正则表达式，定位元素

右击“查看网页源代码”，定位图片路径的位置

import re
def down_load(content):
    #获取图片路径和图片名称
    pattern = re.compile('<div class="box picblock col3".*?<img src2="(.*?)" alt="(.*?)">',re.S)
    a_list = pattern.findall(content)
    for a in a_list:
        url = a[0]
        filename = './meinv/'+a[1] + '.jpg'
        urllib.request.urlretrieve(url=url,filename=filename)

3.完整的代码

(先创建一个“meinv”的文件夹，用来存储图片)

# http://sc.chinaz.com/tag_tupian/OuMeiMeiNv.html
# http://sc.chinaz.com/tag_tupian/OuMeiMeiNv_2.html
# http://sc.chinaz.com/tag_tupian/OuMeiMeiNv_3.html

import urllib.request

def create_request(page):
    base_url = 'http://sc.chinaz.com/tag_tupian/OuMeiMeiNv'
    if page == 1:
        url = base_url + '.html'
    else:
        url = base_url + '_' + str(page) + '.html'

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }

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


def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

import re
def down_load(content):
    pattern = re.compile('<div class="box picblock col3".*?<img src2="(.*?)" alt="(.*?)">',re.S)
    a_list = pattern.findall(content)
    for a in a_list:
        url = a[0]
        filename = './meinv/'+a[1] + '.jpg'
        urllib.request.urlretrieve(url=url,filename=filename)




if __name__ == '__main__':
    start_page = int(input('请输入起始页码'))
    end_page = int(input('请输入结束页码'))
    
    for page in range(start_page,end_page + 1):
        request = create_request(page)
        content = get_content(request)
        down_load(content)