爬虫实例——爬取python百度百科相关一千个词条

Posted 2020-10-01 HHello_World

调度器：

import url_manager,html_downloader,html_parser,html_outputer


class SpiderMain(object):
    """docstring for SpiderMain"""


    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()
                html_cont = self.downloader.download(new_url)
                print(‘craw %d : %s‘ % (count,new_url))
                #print(‘html_cont：%s‘ %(html_cont))

                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 == 1000:
                    break
                count = count + 1
            except:
                print(‘craw failed‘)
            #SpiderMain.f.close()
        self.outputer.output_html()
        



if __name__=="__main__":
    root_url = "https://baike.baidu.com/item/Python"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

url管理器：

class UrlManager(object):
    """docstring for UrlManager"""
    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)
        #print (self.old_urls)
        return new_url

    
    

网页下载器：

import requests
import requests.packages.urllib3.util.ssl_
requests.packages.urllib3.util.ssl_.DEFAULT_CIPHERS = ‘ALL‘

class HtmlDownloader(object):
    """docstring for HtmlDownloader"""
    
    def download(self,url):
        if url is None:
            return None
        #f.write("In downloader,url is %s" % (url))
        #print("In downloader,url is %s" % (url))
        response = requests.get(url)
        response.encoding = "utf-8"
        #f.write("In downloader")
        #print("In downloader,res is %s" % (response.status_code))
        if response.status_code != 200:
            return None
        
        return response.text

        

网页解析器：

from bs4 import BeautifulSoup
import re
import urllib.parse

class HtmlParser(object):
    """docstring for HtmlParser"""
    
    def _get_new_urls(self,page_url,soup):
        new_urls = set()
        links = soup.find_all(‘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 = {}

        #url
        res_data[‘url‘] = page_url

        #<dd class="lemmaWgt-lemmaTitle-title">  <h1 >Python</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):
        #print("in parse")
        if page_url is None or html_cont is None:
            return
        soup = BeautifulSoup(html_cont,‘html.parser‘)
        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：

import spider_main
class HtmlOutputer(object):
    """docstring for HtmlOutputer"""

    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("<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‘])
            fout.write("<td>%s</td>"%data[‘summary‘])
            fout.write("</tr>")
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")