p1-1

 copy
# -*-coding=utf-8-*-    
import os    
import re    
import time    
from urllib.parse import urljoin    
from selenium import webdriver    
import requests    
from bs4 import BeautifulSoup    
from url_decode import urldecode    
    
    
class GovSpider:    
    
    def __init__(self):    
    
        self.site_url = 'http://www.jiangxi.gov.cn/kzw/jxszfxxgkml/zfjg/zfld_12550/'    
    
        self.spath = re.sub('.*//', '', self.site_url)    
    
        sindex = self.spath.find('/')    
    
        if sindex != -1:    
            self.spath = self.spath[:sindex]    
    
        self.base_path = '~/Desktop/gov_spider/'+self.spath    
        print('base:',self.base_path)    
    def start_page(self):    
    
        req = webdriver.Chrome()    
        req.get(self.site_url)    
        time.sleep(3)    
        html1 = req.page_source    
        soup = BeautifulSoup(html1,'lxml')    
        iframes = soup.findAll('iframe')    
    
        self.gs_runner(urldecode(html1))    
    
        if iframes:    
            print('有隐藏页面:',iframes)    
            for ifr_url in iframes:    
    
                if 'https:' not in ifr_url or 'http' not in ifr_url:    
                    ifr_url = urljoin(self.site_url,ifr_url.get('src'))    
                    print('进入隐藏页面：',ifr_url,'，并开启隐藏页面抓取img、css、js的程序........')    
                try:    
                    html2 = requests.get(ifr_url).text    
    
                    self.gs_runner(urldecode(html2))    
                except Exception as e:    
                    print('隐藏页面的地址格式不正确,无法访问：',ifr_url)    
    
    
        #程序运行完毕，自动关闭浏览器    
        req.quit()    
    
    
    def download_imgs(self,html):    
    
        # 多筛选 防止无格式或不在src下的图片漏下    
               liResult = re.findall('(".*?")',html)    
    
        if liResult:    
            print('>>>>>>>>>>>>>>>>>>>>>>>>>正在下载img文件>>>>>>>>>>>>>>>>>>>>>>>>>')    
            for img_li in liResult:    
                        if img_li and ('{' not in img_li and '</' not in img_li) and('.jpg' in img_li or '.ico' in img_li or '.png' in    
                           img_li or '.svg' in img_li or '.gif' in img_li or '.webp' in img_li or 'data:image' in img_li):    
    
                            if '\/' not in img_li:    
                                img_urls = [re.sub('[";]|(.*=)|(.*)|(.*)|(")','',img_li)]    
                            else:    
                                img_urls = [re.sub('[";]','',img_li).replace('\/\/','//').replace('\/','//')]    
    
                            if ',' in img_urls[0]:    
                                print('检测到有js代码中有多路径img_url，正在深入抓取......')    
                                img_urls = img_urls[0].split(',')    
                            for img_url in img_urls:    
    
                                try:    
                                    if 'http:' not in img_url or 'https:' not in img_url:    
    
                                        img_url = urljoin(self.site_url,img_url)    
    
                                    img_name = re.sub('(.*//)', '', img_url)    
    
                                    f_index = img_name.find('/')    
    
                                    l_index = img_name.rfind('/')    
                                    dir_path = self.spath+img_name[f_index:l_index]    
    
                                    if not os.path.exists(dir_path):    
    
                                        os.system('mkdir -p %s'%dir_path)    
    
                                    img_name = re.sub('(.*/)', '', img_url)    
                                    print('正在下载img文件：',img_url)    
                                    img = requests.get(img_url).content    
    
                                    with open('./%s' % (dir_path + '/' + img_name), 'wb') as f:    
                                        f.write(img)    
                                except Exception as e:    
                                    print(img_url,e,'\r\nthis is uvaild url')    
    
            print('===========================img文件下载完毕=============================')