Python35爬虫爬取百度歼击机词条

1.  spider_main

# coding:utf8
from Spider_Test 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 == 7:
                    break
                
                count = count + 1
            except:
                print("craw fail")           
            
        self.outputer.output_html()           

if __name__ == "__main__":
    root_url = "http://baike.baidu.com/view/114149.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

　　2. url_manager

# coding:utf8

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)  #  this place use the method      
        
    def add_new_urls(self, urls):
        if urls is None or len(urls) == 0:
            return        
        for url in urls:           
            self.add_new_url(url)   #  this place use the method    
    
    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   

　　3. html_downloader

# coding:utf8
from urllib import request

class HtmlDownloader(object):    
    
    def download(self, url):
        if url is None:
            return None

        # Python3.5 different from Python2.7
        response = request.urlopen(url)
        if response.getcode() != 200:
            return None
        
        return response.read().decode('utf-8','ignore')

　　4. html_parser

# coding:utf8
import re
import urllib
from bs4 import BeautifulSoup

class HtmlParser(object):    
    
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        links = soup.find_all("a", href=re.compile(r"/view/\d+\.htm"))
        for link in links:
            new_url = link['href']
            # different from Python2.7
            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
        #  <dl class="lemmaWgt-lemmaTitle lemmaWgt-lemmaTitle-">
        title_node = soup.find('dl',class_="lemmaWgt-lemmaTitle lemmaWgt-lemmaTitle-").find("h1")
        res_data['title'] = title_node.get_text()  #  the key should be right or it would raise an error 
        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

　　5. html_outputer

# coding:utf8
class HtmlOutPuter(object):
    
    def __init__(self):
        self.datas = []
        
    def collect_data(self, data):
        if data is None:
            return
        self.datas.append(data) #  array use append method
    
    def output_html(self):
        fout = open('output.html','w')
        
        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")
        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>" % data["url"])
            fout.write("<td>%s</td>" % data["title"])  #  .encode('utf-8')不能编码成utf-8
            #  fout.write("<td>%s</td>" % data["summary"].encode('utf-8').decode('gbk','ignore'))
            fout.write("<td>")
            fout.write(data["summary"].encode('utf-8').decode('gbk','ignore')) # this place can't display some characters
            fout.write("</td>")
            fout.write("</tr>")
        
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html")
        fout.close()

　　最终获取的html，有些字符不能显示，查资料，说是用命令cmd /K chcp 65001 但是用控制台查询codepage编码依然是，改动不了，说是windows 控制台的问题，先这样。