Python爬虫实战代码

爬虫运行流程

本次爬取的是搜索python的百度百科实例，对于URL可能是变化的，如果出现爬取失败，则可能是URL和爬取的相关属性发生了变化

爬取一个网站的第一步,就是分析这个网站：

对于爬取一个页面中的所有的可用链接步骤如下；

首先要知道网站的入口URL（要爬取网站的网址）

要爬取内容的URL属性

以下是爬取百度百科的例子

1.百度搜索Python进入词条

2.得到标题属性

3.得到简介的属性

4.得到页面内任意标签的属性

例如以上标签的正则表达式可以表示为："/item/%(*)%.."

至此对于一个百度词条的分析就结束了；

按照流程图，爬虫被分为5个模块

1.调度器模块：

#coding:utf8
import url_manage
import html_download
import html_outputer
import html_parser
class SpiderMain(object):


    def __init__(self):
        self.urls = url_manage.UrlManager()
        self.downloader = html_download.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_outputer.HtmlOutputer()


    def craw(self, root_url):
        count = 1
        #将入口url添加进url管理器
        self.urls.add_new_url(root_url)
        #启动爬虫循环
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print 'craw %d : %s'%(count, new_url)
                #下载页面
                html_cont = self.downloader.download(new_url)
                #解析器
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                self.urls.add_new_urls(new_urls)
                #收集有价值的数据
                self.outputer.collect_data(new_data)
                if(count == 10):
                    break
                count +=1
            except:
                print '爬取失败'
        self.outputer.output_html()


if __name__ == "__main__":
    root_url = "https://baike.baidu.com/item/Python/407313?fr=aladdin"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

URL管理器模块：

#coding : utf8
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 get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

    def has_new_url(self):
        return len(self.new_urls)!=0

下载器模块：

import urllib2
class HtmlDownloader(object):
    def download(self, url):
        if url is None:
            return None
        response = urllib2.urlopen(url)
        if response.getcode() != 200:
            return None
        return response.read()

解析器模块：

from bs4 import BeautifulSoup
import re
import urlparse
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 = urlparse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
        return new_urls


    def _get_new_data(self, page_url, soup):
        res_data = {}
        #< 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()
        #

        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

应用：（收集和输出价值数据，并存入html标签）

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')
        fout.write("")
        fout.write("")
        fout.write("")

        for data in self.datas:
            fout.write("")
            fout.write("" % data[''])
            fout.write("" % data['title'].encode('utf-8'))
            fout.write("" % data['summary'].encode('utf-8'))
            fout.write("")

        fout.write("
%s
%s
%s
")
        fout.write("")
        fout.write("")

        fout.close()

#最后一步输出出现了问题。无法向html标签中写入数据。哪位大神告知下，但是爬取功能是正常的