爬虫实验运行不理想，待处理

分析目标

目标：百科词条python及相关词条 标题和简介
入口页：https://baike.baidu.com/item/Python/407313?fr=aladdin
url格式：
词条url：/item/OpenCV
数据格式：
标题 <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1></dd>
简介<div class="lemma-summary" label-module="lemmaSummary"></div>
页面编码：UTF-8

标准作业
COPY了这个个baikepython3，照抄，也不行，改了起始页面就行了

我根据教程自己改的。但是只能爬一页，还输出不了。也没报错。我就怀疑是parse部分，组成新链接这部分有问题。
#感觉是自己参数设置错了。想不通，验证不了，没人指点。

爬虫调度器：

from baike_spider import url_manager, html_downloader, html_parser,html_outputer


class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.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('craw %d:%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 == 20:
                    break
                count = count + 1
            except:
                print('craw failed')
            
        self.outputer.output_html
    
    



if __name__ == '__main__':
    root_url = "https://baike.baidu.com/item/%E7%88%AC%E6%A8%A1/6775973?fr=aladdin"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

网页下载器：

'''
Created on 2018年10月24日

@author: judy
'''
import urllib


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()

URL管理器：

'''
Created on 2018年10月24日

@author: judy
'''


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

网页解析器：

import re
import urllib
from bs4 import BeautifulSoup


class HtmlParser(object):
    def _get_new_urls(self,page_url,soup):
        new_urls = set()
        links = soup.findall('a',href=re.compile(r'/item/(.*)'))
        for link in links:
            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
        
        #<dd class="lemmaWgt-lemmaTitle-title"><h1>eclipse</h1>
        title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title'").find("h1")
        res_data['title'] = title_node.get_text()
        
        #<div class="lemma-summary" label-module="lemmaSummary">
        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()
        
        return res_data
        
    def parse(self,page_url,html_cont):
        if page_url is None or html_cont is None:
            return
        
        soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
        new_urls = self._get_new_urls(page_url, soup)
        new_data =self._get_new_data(page_url, soup)
        return new_urls,new_data

输出到文件

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')

        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")
        if len(self.datas) == 0:
            print ('empty')

        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>" % data['url'])
            # 默认为ascii，所以要在后面修改为utf8
            fout.write("<td>%s</td>" % data['title'].encode('utf8'))
            fout.write("<td>%s</td>" % data['summary'].encode('utf8'))
            fout.write("</tr>")

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

        fout.close()