Build a Python Baidu Baike Crawler: Step-by-Step Guide

This article demonstrates a Python web crawler that extracts Baidu Baike entries.

Crawler Main Program Entry

from crawler_test.html_downloader import UrlDownLoader
from crawler_test.html_outer import HtmlOuter
from crawler_test.html_parser import HtmlParser
from crawler_test.url_manager import UrlManager

# Crawler main entry
class MainCrawler():
    def __init__(self):
        # Initialize four processors: URL manager, downloader, parser, outputter
        self.urls = UrlManager()
        self.downloader = UrlDownLoader()
        self.parser = HtmlParser()
        self.outer = HtmlOuter()

    def start_craw(self, main_url):
        print('爬虫开始...')
        count = 1
        self.urls.add_new_url(main_url)
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print('爬虫%d,%s' % (count, new_url))
                html_cont = self.downloader.down_load(new_url)
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                # Add parsed URLs to manager, data to outputter
                self.urls.add_new_urls(new_urls)
                self.outer.conllect_data(new_data)
                if count >= 10:  # control number of crawls
                    break
                count += 1
            except:
                print('爬虫失败一条')
        self.outer.output()
        print('爬虫结束。')

if __name__ == '__main__':
    main_url = 'https://baike.baidu.com/item/Python/407313'
    mc = MainCrawler()
    mc.start_craw(main_url)

URL Manager

class UrlManager():
    def __init__(self):
        self.new_urls = set()  # URLs to crawl
        self.old_urls = set()  # Already crawled URLs

    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

Web Page Downloader

from urllib import request

class UrlDownLoader():
    def down_load(self, url):
        if url is None:
            return None
        rt = request.Request(url=url, method='GET')  # Send GET request
        with request.urlopen(rt) as rp:
            if rp.status != 200:
                return None
            return rp.read()  # Read page content

Web Page Parser

import re
from urllib import parse
from bs4 import BeautifulSoup

class HtmlParser():
    def _get_new_url(self, main_url, soup):
        new_urls = set()
        child_urls = soup.find_all('a', href=re.compile(r'/item/(\%\w{2})+'))
        for child_url in child_urls:
            new_url = child_url['href']
            full_url = parse.urljoin(main_url, new_url)
            new_urls.add(full_url)
        return new_urls

    def _get_new_data(self, main_url, soup):
        new_datas = {}
        new_datas['url'] = main_url
        new_datas['title'] = soup.find('dd', class_='lemmaWgt-lemmaTitle-title').find('h1').get_text()
        new_datas['content'] = soup.find('div', attrs={'label-module': 'lemmaSummary'}, class_='lemma-summary').get_text()
        return new_datas

    def parse(self, main_url, html_cont):
        if main_url is None or html_cont is None:
            return
        soup = BeautifulSoup(html_cont, 'lxml', from_encoding='utf-8')
        new_url = self._get_new_url(main_url, soup)
        new_data = self._get_new_data(main_url, soup)
        return new_url, new_data

Output Processor

class HtmlOuter():
    def __init__(self):
        self.datas = []

    def conllect_data(self, data):
        if data is None:
            return
        self.datas.append(data)
        return self.datas

    def output(self, file='output_html.html'):
        with open(file, 'w', encoding='utf-8') as fh:
            fh.write('<html>')
            fh.write('<head>')
            fh.write('<meta charset="utf-8">')
            fh.write('<title>爬虫数据结果</title>')
            fh.write('</head>')
            fh.write('<body>')
            fh.write('<table style="border-collapse:collapse; border:1px solid gray; width:80%; word-break:break-all; margin:20px auto;">')
            fh.write('<tr>')
            fh.write('<th style="border:1px solid black; width:35%;">URL</th>')
            fh.write('<th style="border:1px solid black; width:15%;">词条</th>')
            fh.write('<th style="border:1px solid black; width:50%;">内容</th>')
            fh.write('</tr>')
            for data in self.datas:
                fh.write('<tr>')
                fh.write('<td style="border:1px solid black">{0}</td>'.format(data['url']))
                fh.write('<td style="border:1px solid black">{0}</td>'.format(data['title']))
                fh.write('<td style="border:1px solid black">{0}</td>'.format(data['content']))
                fh.write('</tr>')
            fh.write('</table>')
            fh.write('</body>')
            fh.write('</html>')

The sample output shows a table with URLs, entry titles, and extracted content, confirming that the crawler works as intended.