美拍网图片下载
难度不大,网站对f12和右键有限制,但不是大问题。
网站没有反爬,至少没有给图片加防盗链,下载的图片并不是最高清,但清晰度还可以。
- 多线程代码直接复制之前的,其它的也大部分是走流程,固定套路
- 网站上图片全部为jpg格式,所以无需考虑png格式下载
- 唯一需要注意的是,有些图片src链接并不完整,需要自行判断和补全
网站:https://4zipai.net
使用方式:
先:输入路径
后:输入网址,如:‘https://4zipai.net/selfies/202207/139004.html’
代码
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
| import os import re import threading import requests from bs4 import BeautifulSoup import time
headers = { 'Cookie': '_ga=GA1.2.87052855.1662906879; _gid=GA1.2.106606571.1662906879; twk_idm_key=Szy-fmwxLJBDQNQQ_hKZE; TawkConnectionTime=0; twk_uuid_5e23d8f08e78b86ed8aa0035=%7B%22uuid%22%3A%221.101H94883vBguY180oYHfz0VN3Yrx0pdi2oaeD50URIjcHT13XZdZReDZEMwzt5gW4NEYVHRIUmMAPKTQXzgo0tbdNL6fRa2f2JnkKEdjUC5Me7ZTzLZlaEgUmdlaJJk9PBSm4ORF3UQSw%22%2C%22version%22%3A3%2C%22domain%22%3A%224zipai.net%22%2C%22ts%22%3A1662906990942%7D; __cf_bm=v0FGBMppZPUweg7R0uBuFPrQlE71b0ptig4q4MkaeBU-1662906991-0-AcVALr7cJKi1sMQpzf8Zs1DEJ1PojPDd9mLT8fncCrdyiEBznfws9/awsYksUmTA0dbcUfgPxplYWbTz7LfBSmLvl1dQAD4RU0ni6jxBgdSIvn8SxmBZSJkJCI00EuzjOw==', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36' }
class myThread(threading.Thread): def __init__(self, url, fileName, file_path): threading.Thread.__init__(self) self.url = url self.file_path = file_path self.fileName = fileName
def open_url(self, url): response = requests.get(url, headers) return response.text
def run(self): img = requests.get(self.url, headers=headers) file = self.file_path + "\\" + self.fileName + ".jpg" if not os.path.exists(file): print("Downloading %s" % self.fileName) with open('%s/%s.jpg' % (self.file_path, self.fileName), 'wb') as f: f.write(img.content) else: print(self.file_path + "\\" + self.fileName + " exist")
save_path = input("输入要保存的路径文件夹") url = input("输入网址") rsp = requests.get(url=url, headers=headers) rsp.encoding="UTF-8" soup = BeautifulSoup(rsp.text, 'lxml')
title=soup.find('div',class_="item_title") save_path=save_path+'\\'+ str(title.find("h1").text).strip(" ")
if not os.path.exists(save_path): os.makedirs(save_path) li = soup.find(class_='content_left') for i in li.find_all('img'): each_url=str(i.get('src')) judge = each_url[1] if judge == "d": each_url = "https://4zipai.net/" + each_url name = str(each_url).split('/')[-1].split('.')[0] if len(name) >= 9: thread1 = myThread(each_url, name, save_path) thread1.start() time.sleep(0.1)
|
推荐
/selfies/202208/140912.html
/selfies/202209/142694.html
/selfies/201808/70879.html
/selfies/201804/63980.html
/selfies/201708/48223.html
/selfies/201903/80767.html
/selfies/201804/63878.html
/selfies/202207/139004.html
/selfies/202209/142301.html
/selfies/202209/142402.html
/selfies/202209/142391.html
/selfies/202209/142416.html
/selfies/202208/142269.html
/selfies/202209/142317.html