Python实现简单爬虫逻辑

最新推荐文章于 2022-12-02 17:30:32 发布

飞天德007

最新推荐文章于 2022-12-02 17:30:32 发布

阅读量999

点赞数 1

分类专栏： python 文章标签： python

本文链接：https://blog.csdn.net/u011000635/article/details/78262989

版权

python 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

这里写图片描述
spider_main.py 爬虫调度器

# coding:utf8
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
        #将第一个url添加到待爬取的url
        self.urls.add_new_url(root_url) 
        #判断是否还有未爬取的url
        while self.urls.has_new_url():
            try:
                #获取待爬取的url
                new_url = self.urls.get_new_url()
                print('craw %d : %s' % (count,new_url))
                #根据url下载该网页的内容
                html_cont = self.downloader.download(new_url)
                #解析下载网页的内容,将新获取的ur添加到待爬取列表,获取到想要爬取的内容
                new_urls, new_data = self.parser.parse(new_url,html_cont)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_date(new_date)

                if count == 1000:
                    break

                count = count + 1
            except:
                print('craw failed')
        #将爬取到的内容输出到html中
        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管理器 url_manager.py


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

网页下载器 html_downloader.py

import urllib

class HtmlDownloader(object):

    def download(self,url):
        if url is None:
            return None

        response = urllib.urlopen(url)

        if response.getcode() != 200:
            return None

        return response.read()

网页解析器 html_parser.py

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) #疑问调用自己的方法是要加下划线吗
        new_urls = self._get_new_data(page_url,soup)
        return new_urls,new_urls

    def _get_new_urls(self,page_url,soup):
        #/item/Python/407313
        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,html_cont):
        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

将爬取到的价值数据输出 html_outputer.py


class HtmlOutputer(object):

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

    def collect_date(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>")
        fout.write("</table>")
        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>"% data['url'].encode('utf-8'))
            fout.write("<td>%s</td>"% title['title'].encode('utf-8'))
            fout.write("<td>%s</td>"% summary['url'].encode('utf-8'))
            fout.write("</tr>")
        fout.write("</body>")
        fout.write("</html>")

        fout.close()

飞天德007

关注

1
点赞
踩
5

收藏

觉得还不错? 一键收藏
0
评论
Python实现简单爬虫逻辑

spider_main.py 爬虫调度器# coding:utf8import url_manager,html_downloader,html_parser,html_outputerclass SpiderMain(object): def __init__(self): self.urls = url_manager.UrlManager() sel
复制链接

扫一扫