Python爬取百度百科1000个页面的数据

最新推荐文章于 2024-08-31 18:51:53 发布

置顶我是一片小树叶

最新推荐文章于 2024-08-31 18:51:53 发布

阅读量438

点赞数

分类专栏： Python学习初涉文章标签： python 爬虫百度百科1000个页面

本文链接：https://blog.csdn.net/qq_30534935/article/details/94015953

版权

Python学习初涉专栏收录该内容

14 篇文章 1 订阅

订阅专栏

本文详细介绍了使用Python进行网络爬虫，成功抓取了百度百科的1000个页面数据，涵盖了爬虫的实现过程和技术要点。

摘要由CSDN通过智能技术生成

# _*_ coding:utf8 _*_

import urllib.request
import urllib.parse
from bs4 import BeautifulSoup
import re


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


class HtmlDownloader(object):
    def download(self,url):
        if url is None:
            return None
        response = urllib.request.urlopen(url,timeout=1)
        if response.getcode() != 200:
            return None
        return response.read()


class HtmlParser(object):
    def _get_new_urls(self,page_url,soup):
        new_urls = set()
        #/%s/%d
        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">
        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


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',encoding="utf-8")
        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")
        #ascii
        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()

    
class SpiderMain(object):
    def __init__(self):
        self.urls = UrlManager()
        self.downloader = HtmlDownloader()
        self.parser = HtmlParser()
        self.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 == 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)

具体讲解参见：https://blog.csdn.net/qq_30534935/article/details/93776392