#/usr/bin/env python
#coding:utf-8import json
import urllib.request
import threading
#导入需要的JSON ，urllib及threading
#定义一个类
class myThread(threading.Thread):def __init__(self,imgurl,filename):threading.Thread.__init__(self)self.imgurl = imgurlself.filename = filenamedef run(self):print ('downloading: ' + self.imgurl)downfile(self.imgurl,self.filename)
#定义一个下载程序
def downfile(imgurl , filename):img_req = urllib.request.Request(imgurl)opener = urllib.request.build_opener()img_resp = opener.open(img_req)try:out = open(filename,'wb')out.write(img_resp.read())out.flush()out.close()except:print('error')if __name__ == "__main__":surl = 'http://huaban.com/pins/1821121555/?jlb0k0ki'#需要爬取的花瓣网美女图片地址hb = urllib.request.Request(surl)#按XHLHttprequest方式请求hb.add_header('X-Requested-With','XMLHttpRequest' )#模拟win10 chrome 浏览器hb.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/53.0')html = urllib.request.urlopen(hb).read()obj = json.loads( html )#print (obj['pin']['board']['pins'])imgs = obj['pin']['board']['pins']#花瓣网图片需要的网址头preurl = 'http://img.hb.aicdn.com/'for img in imgs :imgurl = preurl + img['file']['key']#print (imgurl)myThread(imgurl,img['file']['key'] + '.jpg').start()

import urllib.request
import re
import os
import datetime
import easygui# 获取网页
def get_html(url):page = urllib.request.urlopen(url)html = page.read().decode('utf-8')     #需要解码return html# 下载图片
def get_image(path,html):# 获取HTML源码里面的app.page["pins"]部分，主要图片ID位于此部分get_app_page_pins = re.compile(r'app\.page\["pins"\].*?;', re.S)get_str = re.findall(get_app_page_pins, html)[0]pin_id = r'"pin_id":(\d+)'pin_id_re = re.compile(pin_id)# 获取图片ID，保存在列表中id_list = re.findall(pin_id_re,get_str)x = 0for pinId in id_list:# 获取跳转网页网址url_str = r'http://huaban.com/pins/%s/' % pinId# 获取点击图片时弹出网页的源码pinId_source = get_html(url_str)# 解析源码，获取原图片的网址img_url_re = re.compile('main-image.*?src="(.*?)"', re.S)img_url_list = re.findall(img_url_re, pinId_source)try:img_url = 'http:' + img_url_list[0]urllib.request.urlretrieve(img_url, path + '\%s.jpg' % x)except:print("获取图片：%s失败，跳过，获取下一张。" % img_url)continueprint("获取成功！%s" % img_url)x += 1print("保存图片成功！")# 创建文件夹路径
def createPath():while True:print('选择你要保存的路径')path = easygui.diropenbox()filePath = path + "\\" + str(datetime.datetime.now().strftime('%Y-%m-%d %H.%M.%S'))isExists = os.path.exists(filePath)if not isExists:# 创建目录os.makedirs(filePath)print('%s创建成功！' % filePath)breakelse:print('%s已存在重新输入！' % filePath)return filePathif __name__ == '__main__':html = get_html("http://huaban.com/favorite/beauty/")get_image(createPath(), html) #调用创建文件夹方法并返回文件夹路径和传入网址

#-*- coding:utf-8 -*-
import requests
import re
import json
# 导入 requests  re正则 json'''
login
登录花瓣 获取session
'''
def login():login_url = 'https://huaban.com/auth/'# 登录地址headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0","Accept": "application / json","Content-type": "application/x-www-form-urlencoded; charset=utf-8","Referer": "https://huaban.com/",}# 请求头信息session = requests.session()#sesson 会话login_data = {"email": "zengmumu%40126.com","password": "zmm123","_ref":"frame"}response = session.post(login_url, data=login_data, headers=headers,verify=False)# 登录页面getPic(session,5)# 获取图片，前5页'''
getPic
解析页面中的图片地址
session 会话信息
num     最大是页数
'''
def getPic(session,num):for i in range(1,num+1):response = session.get("https://huaban.com/search/?q=%E5%A5%B3%E7%A5%9E&category=photography&page="+str(i))# 获取页面信息("美女"文字编码后的结果是"%E5%A5%B3%E7%A5%9E" )data = re.search('app\.page\[\"pins\"\] =(.*);\napp.page\[\"page\"\]', response.text, re.M | re.I | re.S)# 提取到当前页面所在的所有图片信息data = json.loads(data.group(1))# 转换字符串为列表for item in data:url = "https://hbimg.huabanimg.com/" + item["file"]["key"]# 拼接图片地址index = item["file"]["type"].rfind("/")type = "."+item["file"]["type"][index + 1:]# 获取图片的类型file_name = item["raw_text"]# 获取图片的中文名download_img(url, file_name,type)# 下载图片'''
下载图片
url        图片的地址
name   图片的中文名
type     图片的类型
'''
def download_img(url,name,type):response = requests.get(url,verify=False)# 使用requests 下载图片index = url.rfind('/')file_name = name+url[index + 1:]+type# 获取图片的hash值print("下载图片：" + file_name)# 打印图片名称save_name = "./photo/" + file_name# 图片保存的地址(注意photo要自己建一个，与当前.py文件同一个文件夹)with open(save_name, "wb") as f:f.write(response.content)# 写入图片到本地
'''
定义主函数
'''
def main():login()# 如果到模块的名字是__main__ 执行main主函数
if __name__ == '__main__':main()