Python實作簡單爬蟲

簡介

爬蟲是一段自動抓取網路資訊的程式。它的價值是互聯網數據為我所有。利用爬取到的數據，可以做很多的事情如：可以進行數據統計，對比；可以利用爬取的數據做某一方面的app；也可以利用爬取的數據做一個新聞閱讀器等等。

爬蟲架構

1）URL管理器 
2）網頁下載器 
3）網頁分析器 
4）爬蟲調用者 
5）價值資料使用

蟲實現

蟲實現

2）URL管理器實作

# coding:utf-8
import url_manager
import html_downloader
import html_parser
import html_outputer
import url_manager
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
        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 = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

3）URL下載器實作

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

4）URL解析器實作

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()

5）價值資料輸出顯示

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"/view/\d+\.htm"))
        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 = {}
        res_data['url'] = page_url
        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

關鍵字相關的1000個靜態網頁，對網頁中的數據，主要提取關鍵字和摘要信息，並將爬取的信息以HTML文件的方式存儲，之後利用瀏覽器打開即可實現訪問。