网页抓取数据百度百科(爬虫自动抓取互联网信息的程序-苏州安嘉网络 )

　　网页抓取数据百度百科(爬虫自动抓取互联网信息的程序-苏州安嘉网络

)

　　爬虫是一种自动从互联网上抓取信息的程序。通常，少量信息是从互联网上手动获取的。爬虫可以从一个 URL 开始，访问与之关联的 URL，并从每个页面获取有价值的数据。

　　

　　这是一款轻量级（无需登录和异步加载静态网页抓取）开发的网络爬虫，用python语言编写，主要包括URL管理器、网页下载器（urllib2)、网页解析器（BeautifulSoup）），以实现百度百科爬虫入口相关的N个（自行设置）页面数据。简单爬虫的结构如下：

　　

　　简单的爬虫架构流程如下：

　　

　　程序根据架构分为以下五个主要的py文件：

　　

　　主要的调度文件是spider_main.py

　　#coding:utf8

import html_outputer

import html_parser

import url_manager

import html_downloader

class SpiderMain(object):

def __init__(self):

self.urls = url_manager.UrlManager()

self.downloader = html_downloader.HtnlDownloader()

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 == 10:

break

count = count + 1

except:

print 'craw failed'

self.outputer.output_html()

if __name__ == "__main__":

root_url = "http://baike.baidu.com/item/%E7%BD%91%E7%BB%9C%E7%88%AC%E8%99%AB"

obj_spider = SpiderMain()

obj_spider.craw(root_url)

　　URL 管理器 url_manager.py

　　#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 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

　　htmldownloaderhtml_downloader.py

　　#coding:utf8

import urllib2

class HtnlDownloader(object):

def download(self, url):

if url is None:

return None

response = urllib2.urlopen(url)

if response.getcode()!=200:

return

return response.read()

　　html 解析器 html_parser.py

　　# coding:utf8

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 = {}

res_data['url'] = page_url

#Python

title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")

res_data['title'] = title_node.get_text()

#

para_node = soup.find('div',class_="para")

res_data['para'] = para_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

　　html 输出器 html_outputer.py

　　#coding:utf8

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("")

#ascii

for data in self.datas:

fout.write("")

fout.write("%s"%data['url'])

fout.write("%s"%data['title'].encode('utf-8'))

fout.write("%s"%data['para'].encode('utf-8'))

fout.write("")

fout.write("")

fout.write("")

fout.write("")

fout.close()

　　爬取的结果：