亿秀图片爬取

亿秀图片爬取
科技前沿 • 2025-04-11 16:13 • 阅读 42
大家好，我是讯享网，很高兴认识大家。
import requests
from requests.exceptions import RequestException
import re
import time
number=0
def get_one_html(url):
    try:
        response=requests.get(url)
        response.encoding = 'utf-8'  # 定义编码
        if response.status_code==200:
            return response.text
        return None
    except RequestException:
        return None

def get_all_url():
    for i in range(1,20):
        url="http://www.tu11.com/xingganmeinvxiezhen/list_1_{}.html".format(i)
        time.sleep(1)
        html=get_one_html(url)
        #print(html)
        reuserid = re.compile(' <div class="shupic".*?a href="(.*?)" target="_blank"><img class="', re.S)
        itemsuser = re.findall(reuserid, html)
        get_jpg_url(itemsuser)

def get_jpg_url(items):
    for item in items:
        html = get_one_html("http://www.tu11.com"+item)
        get_number_jpg(html)
        for i in range(1,get_number_jpg(html)):
            if i>1:
                a = item.strip()[:-5]+"_{}.html".format(i)
                print(a)
            else:
                a=item
                print(a)
            html = get_one_html("http://www.tu11.com" + a)
            reuserid = re.compile('<p align="cen.*?img src="(.*?)".*?</p><br/', re.S)
            items = re.findall(reuserid,html)
            if len(items)>0:
                print(items)
                write_ipg_loding(items)

def get_number_jpg(html):  #获得当前页数
    reuserid = re.compile('ist-inline text-center nryfy"><li><a>��(.*?)ҳ:', re.S)
    item = re.findall(reuserid, html)
    return int(item[0])

def write_ipg_loding(images):
    global number
    for image in images:
        response=requests.get(image)
        with open('C:\\Users\\Administrator\\Desktop\\test\\'+str(number) + '.jpg', 'wb') as f:
            print("正在写入第%d"%number)
            f.write(response.content)
            f.close()
            number=number+1
if __name__=="__main__":

    get_all_url()


#/xingganmeinvxiezhen/2018/10900_2.html
讯享网
相关推荐
