One Piece 海贼王动漫壁纸 Python 爬取！

https://www.ivsky.com/bizhi/one_piece_t571/

https://www.ivsky.com/bizhi/one_piece_t571/index_2.html

import requests,time
from lxml import etree

hrefs=tree.xpath('//ul[@class="il"]/li/div[@class="il_img"]/a/@href')

img_url=tree.xpath('//img[@id="imgis"]/@src')[0]

# one_piece 天堂图片网 图片采集
# https://www.ivsky.com/bizhi/one_piece_t571/index_2.html
# 20211105 by 微信：huguo00289
# -*- coding: UTF-8 -*-
import requests,time
from lxml import etree


def get_imghrefs(url):
    # url = "https://www.ivsky.com/bizhi/one_piece_t571/index_2.html"
    headers={"user-agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"}
    response=requests.get(url=url,headers=headers,timeout=6)
    print(response.status_code)
    html=response.content.decode('utf-8')
    tree=etree.HTML(html)
    hrefs=tree.xpath('//ul[@class="il"]/li/div[@class="il_img"]/a/@href')
    print(len(hrefs))
    print(hrefs)

    img_hrefs=[]
    for href in hrefs:
        href=f'https://www.ivsky.com{href}'
        img_hrefs.append(href)

    return img_hrefs


def get_img(url):
    #url="https://www.ivsky.com/bizhi/one_piece_v36640/pic_599277.html"
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"}
    response = requests.get(url=url, headers=headers, timeout=6)
    print(response.status_code)
    html = response.content.decode('utf-8')
    tree = etree.HTML(html)
    img_url=tree.xpath('//img[@id="imgis"]/@src')[0]
    img_url =f'https:{img_url}'
    imgname=img_url.split('/')[-1]
    print(img_url,imgname)
    img=img_url,imgname
    return img


def down_img(img):
    # img_url="https://img-pre.ivsky.com/img/bizhi/pre/201606/21/one_piece-005.jpg"
    # imgname="one_piece-005.jpg"
    img_url=img[0]
    imgname=img[1]
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"}
    r = requests.get(url=img_url, headers=headers, timeout=6)
    with open(imgname,'wb') as f:
        f.write(r.content)
    print(f">> 下载 {imgname} 图片成功！")



def main():
    url="https://www.ivsky.com/bizhi/one_piece_t571/index_2.html"
    img_hrefs=get_imghrefs(url)
    for img_href in img_hrefs:
        img=get_img(img_href)
        down_img(img)
        time.sleep(1)



if __name__=='__main__':
    main()

# one_piece 天堂图片网 图片采集
# https://www.ivsky.com/bizhi/one_piece_t571/index_2.html
# 20211105 by 微信：huguo00289
# -*- coding: UTF-8 -*-
import requests,time,os
from lxml import etree
import threading


class One():
    def __init__(self,url,pagenum):
        self.headers = {
            "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"}
        self.url=url
        self.pagenum=pagenum
        pathname=url.split('/')[-2]
        self.path=f'{pathname}/'
        os.makedirs(self.path,True)


    def get_img_herfs(self):
        for page in range(1,self.pagenum+1):
            if page==1:
                url=self.url
            else:
                url=f'{self.url}index_{page}.html'
            self.get_imghrefs(page,url)




    def get_imghrefs(self,page,url):
        print(f">> 正在爬取 第{page}页 链接：{url}")
        response=requests.get(url=url,headers=self.headers,timeout=6)
        html=response.content.decode('utf-8')
        tree=etree.HTML(html)
        hrefs=tree.xpath('//ul[@class="il"]/li/div[@class="il_img"]/a/@href')
        print(len(hrefs))
        print(hrefs)
        self.thread_get_imgs(page,hrefs)



    def thread_get_imgs(self,page,hrefs):
        threadings=[]
        for href in hrefs:
            href=f'https://www.ivsky.com{href}'
            t=threading.Thread(target=self.get_img,args=(href,page))
            threadings.append(t)
            t.start()

        for x in threadings:
            x.join()

        print("多线程下载图片完成")



    def get_img(self,url,page):
        response = requests.get(url=url, headers=self.headers, timeout=6)
        html = response.content.decode('utf-8')
        time.sleep(1)
        tree = etree.HTML(html)
        img_url=tree.xpath('//img[@id="imgis"]/@src')[0]
        img_url =f'https:{img_url}'
        img_name=img_url.split('/')[-1]
        img_name=f'{page}_{img_name}'
        print(img_url,img_name)
        self.down_img(img_url,img_name)



    def down_img(self,img_url,img_name):
        r = requests.get(url=img_url, headers=self.headers, timeout=6)
        with open(f'{self.path}{img_name}','wb') as f:
            f.write(r.content)
        print(f">> 下载 {img_name} 图片成功！")





def main():
    url="https://www.ivsky.com/bizhi/one_piece_t571/"
    pagenum=12
    spider=One(url,pagenum)
    spider.get_img_herfs()



if __name__=='__main__':
    main()