【3月20日】Python自制简易爬虫框架_python 爬虫框架自制-优快云博客

本文链接：https://blog.youkuaiyun.com/Moon_treee/article/details/64228202

本文介绍了一个简易的爬虫框架，包括URL管理器、HTML下载器、HTML解析器及HTML输出器四大模块。该框架实现了网页爬取的基本流程，从管理待爬取和已爬取的URL到下载网页内容、解析并提取所需数据，最后将数据输出为HTML文件。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

简易框架由以下几个模块：

url管理器：管理网址new_urls存放未爬取的网址的集合，old_urls存放已经爬取网址的集合
html下载器：使用urllib.request.urlopen（python3）对html资源进行下载
html解析器：使用BeautifulSoup对页面内容进行解析
html输出器：对爬取的结果封装成html文件输出

url管理器

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

html下载器

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()

html解析器

from bs4 import BeautifulSoup
import re
import urllib.parse


class HtmlParser(object):
    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

    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        links = soup.find_all('a', href=re.compile(r"/item/\w+"))
        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>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

html输出器

class 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>')
        fout.close()

main

from baike_spider import html_downloader
from baike_spider import html_outputer
from baike_spider import html_parser
from baike_spider import url_manager


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 == 100:
                    break
                count += 1
            except:
                print("craw failed")

        self.outputer.output_html()


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