编写豆瓣相册下载器（python爬虫）

最近在慕课网上学习了一门python爬虫课程《Python开发简单爬虫》，并利用课程中学到的知识自己编写了一个豆瓣相册爬虫，可以一键快速下载豆瓣相册中的图片，并且会自动下载大图。

在这里将这个爬虫分享出来，因为网络上的豆瓣相册下载器基本上都不能使用了，所以才想到自己开发一个，方便大家使用。

一、程序代码

github: https://github.com/xinxingli/douban_spider

本地下载：

二、爬虫运行截图

三、主要程序代码

调度程序 spider_main.py

from douban_spider import url_manger
from douban_spider import html_downloader
from douban_spider import html_parser
from douban_spider import html_outputer

class SpiderMain(object):
    def __init__(self):
        self.urls = url_manger.UrlManager()
        self.downloader = html_downloader.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_outputer.HtmlOutputer()

    def craw(self, root_url):
        count = 1
        self.urls.add_new_url(root_url)
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print('爬取第 %d 页: %s' %(count, new_url))
                html_cont = self.downloader.download(new_url)
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)

                if count == 10:
                    break
count = count + 1
            except:
                print('craw failed')
        self.outputer.output_html()


if __name__ == '__main__':
    str = input("请输入要下载的豆瓣相册ID(例如1639309626): ")
    root_url = 'https://www.douban.com/photos/album/'+str+'/'
print('即将开始下载相册： %s ' % root_url)
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

网址管理程序 url_manger.py :

class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()

    def add_new_url(self, url):
        if url is None:
            return
        if url not in self.new_urls and url not in self.old_urls:
            self.new_urls.add(url)

    def add_new_urls(self, urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(url)

    def has_new_url(self):
        return len(self.new_urls) != 0

    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

网页下载程序 html_downloader.py ：

#from urllib import request
import urllib.request

class HtmlDownloader(object):
    def download(self,url):
        if url is None:
            return None
response = urllib.request.urlopen(url)

        if response.getcode() != 200:
            return None
        return response.read()

解析程序html_parser.py ：

from bs4 import BeautifulSoup
import re
import urllib.parse
import urllib.request

class HtmlParser(object):
    def _get_new_urls(self,page_url,soup):

        new_urls = set()

        links = soup.find_all('img',width="201")
        for link in links:
            photo_url = link['src']
            photo_url_list = list(photo_url)
            photo_url_list[37] = 'l'               
photo_url = ''.join(photo_url_list)     

            photo_name = photo_url[46:57] #取出连接中的图片名称
print('正在下载图片：%s.jpg'% photo_name)

            urllib.request.urlretrieve(photo_url, 'photo/%s.jpg' % photo_name)


        pages = soup.find_all('a', href=re.compile(r'https://www.douban.com/photos/album/\w*/\?start'))
        for link in pages:
            new_url = link['href']
            new_full_url = urllib.parse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
        return new_urls

    def _get_new_data(self,page_url,soup):
        res_data={}
        res_data['url'] = page_url
        return res_data

    def parse(self,page_url,html_cont):
        if page_url is None or len(html_cont)==0 :
            return None
soup = BeautifulSoup(html_cont,'html.parser',from_encoding='iso-8859-1')
        #from_encoding='iso-8859-1'
new_urls = self._get_new_urls(page_url,soup)
        new_data = self._get_new_data(page_url,soup)
        return new_urls,new_data

输出程序 html_outputer.py ：

class HtmlOutputer(object):
    def __init__(self):
        self.datas = []

    def collect_data(self, data):
        if data is None:
            return
self.datas.append(data)

    def output_html(self):
        fout = open('output.html', 'w', encoding="utf-8")

        fout.write("<html>")
        fout.write("<head><meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\"></head>")
        fout.write("<body>")
        fout.write("<table>")

        for data in self.datas:
            fout.write("<tr>")
            fout.write("<img ")
            fout.write("width=\"201\" src=%s />"% data['url'] )
            fout.write("</tr>")

        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")
        fout.close()

---