Python 爬虫项目示例

创建 python 爬虫项目，从上图左至右，创建5个类：

主类：SpiderMain

URL管理类：UrlManager

网页下载类：HtmlDownloader

网页解析类：HtmlParser

输出类：HtmlOutputer

主类：SpiderMain

# coding:utf8

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_url, new_data = self.parser.parse(new_url, html_cont)
                self.urls.add_new_urls(new_url)
                self.outputer.collect_data(new_data)
                if count == 1000:
                    break
                count = count + 1
            except:
                print("craw failed")
        
        self.outputer.output_html()
        
if __name__=="__main__":
    root_url = "https://baike.baidu.com/item/Python/407313"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

URL管理类：UrlManager

# coding:utf8

class UrlManager(object):
    def __init__(self):
        self.new_urls = set() #待爬取url集合
        self.old_urls = set() #已爬取url集合

    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

网页下载类：HtmlDownloader

# coding:utf8
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()

网页解析类：HtmlParser

# coding:utf8
import re
from bs4 import BeautifulSoup
import urllib.parse as urlparse

class HtmlParser(object):
        
        
        def _get_new_urls(self, page_url, soup):
            new_urls = set()
            # /item/%E9%9B%86%E6%88%90%E5%BC%80%E5%8F%91%E7%8E%AF%E5%A2%83
            links = soup.find_all('a',href=re.compile(r"/item/.*"))
            for link in links:
                new_url = link['href']
                new_full_url = urlparse.urljoin(page_url,new_url)
                new_urls.add(new_full_url)
            return new_urls
        
        def _get_new_date(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_cout):
            if page_url is None or html_cout is None:
                return
            soup = BeautifulSoup(html_cout,'html.parser')
            new_urls = self._get_new_urls(page_url,soup) #当前页面的所有网址
            new_data = self._get_new_date(page_url,soup) #当前页面的 title、summary
            return new_urls, new_data

输出类：HtmlOutputer

# coding:utf8

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>")
        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'))
            fout.write("<td>%s</td>" % data['summary'].encode('utf-8'))
            fout.write("</tr>")
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")
    

原视频教程： Python开发简单爬虫