python 网页爬虫（URL）

最新推荐文章于 2024-02-19 22:56:04 发布

lichar03

最新推荐文章于 2024-02-19 22:56:04 发布

阅读量647

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/lichar03/article/details/78335338

版权

python 专栏收录该内容

16 篇文章 0 订阅

订阅专栏

这是一篇课程总结。

课程来源: 慕课网

需要爬网页做成pdf方便打印。

Module 分成五个部分：网页下载器，网页解析器，网页信息的输出，，URL管理，主调度程序。

Python 3.5+，需要用到urllib2 re urlparse bs4 四个库。

主调度程序：

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.HtmlOuputer()
    #爬虫的调度程序
    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)
            except Exception as err:
                print(err.__str__())
                print('craw failed')

            if count==1000:
                break
            count+=1


        self.outputer.output_html()



if __name__ == '__main__':
    #要爬取得URL
    root_url='https://baike.baidu.com/item/Google'
    obj_spider=SpiderMain()
    obj_spider.craw(root_url)

网页管理器：

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)
        return

    def add_new_urls(self, urls):
        if urls is None or len(urls)==0:
            return
        for url in urls:
            self.add_new_url(url)
        return

    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：

from  urllib import request

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

        response=request.urlopen(url)

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

        return  response.read()

网页解析：

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

class HtmlParser(object):
    def _get_new_urls(self, page_url, soup):
        new_urls=set()
        links=soup.find_all('a',href=re.compile(r'/item/'))
        for link in links:
            new_url=link['href']
            new_full_url=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')
        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_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

网页输出：

class HtmlOuputer(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("<head><meta http-equiv='content-type' content='text/html;charset=utf-8'></head>")
        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'])

爬取结果：