百度百科首页html,爬取百度百科N个页面的数据

目标：百度百科Python词条相关词条网页 - 标题和简介

URL格式：

词条页面URL：/item/Python

数据格式：

标题

Python

简介

页面编码：

UTF-8

调度程序 spider_main.py

#coding:utf8

import html_downloader, html_parser, html_outputer,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 == 10:

break

count+=1

except:

print 'craw failed'

self.outputer.output_html()

if __name__=="__main__":

root_url = "http://baike.baidu.com/item/Python"

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

HTML下载器 html_downloader.py

#coding:utf8

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()

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 = {}

#url

res_data['url'] = page_url

#

Python

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

HTML输出器 html_outputer.py

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("

")

fout.write("

for data in self.datas:

fout.write("

")

fout.write("

%s" % data['url'])

fout.write("

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

fout.write("

%s" % data['summary'].encode('utf-8'))

fout.write("

")

fout.write("

")

fout.write("")

fout.write("")

fout.close()