您的位置：首页 > 其它

百度百科爬虫

2016-04-24 20:05 225 查看

<span style="background-color: rgb(255, 255, 255); font-family: Arial, Helvetica, sans-serif;">在慕课网http://www.imooc.com/learn/563 上学了爬虫，今天特此记录一下</span>

一共分5个模块，分别是主函数，url管理，html下载，html分析，html输出。

先创建5个.py文件，命名为 spider_main, url_manager, html_downloader, html_parser, html_outputer

一.spider_main

一开始提示，找不到baike_spider包，所以加了两句话

import sys

sys.path.append(r'F:\1234\imooc')

<span style="font-size:18px;"># -*- coding: utf-8 -*-
import sys
sys.path.append(r'F:\1234\imooc')
from baike_spider import url_manager, html_downloader, html_parser, html_outputer

class SpiderMain():
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):
#try:
count = 1
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
new_url = self.urls.get_new_url()
print 'crow %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 == 2:
break

count += 1
#except:
#    print 'crow 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)
</span><span style="font-size: 32px;">

</span>

二.url_maneger.py

<span style="font-size:18px;"># -*- coding: utf-8 -*-

class UrlManager():
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</span><span style="font-size:24px;">

</span>

三.html_downloader.py

<span style="font-size:18px;"># -*- coding: utf-8 -*-
import urllib2

class HtmlDownloader():

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

response = urllib2.urlopen(url)

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

return response.read()
</span>

四.html_parser.py

<span style="font-size:18px;"># -*- coding: utf-8 -*-

from bs4 import BeautifulSoup
import re
import urlparse

class HtmlParser():

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 = {}

# url
res_data['url'] = page_url

# <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()

# <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</span><span style="font-size:24px;">
</span>

五.html_outputer.py

由于一开始输出都是乱码，所以去找了一下在<html>和<body>之间加入fout.write("<head>") fout.write('<meta charset="utf-8">') fout.write("</head>")

<span style="font-size:18px;"># -*- coding: utf-8 -*-
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

class HtmlOutputer():

def __init__(self):
self.data = []

def collect_data(self, data):
if data is None:
return
self.data.append(data)

def output_html(self):
fout = open('output.html', 'w')

fout.write('<html>')
fout.write("<head>")
fout.write('<meta charset="utf-8">')
fout.write("</head>")
fout.write('<body>')
fout.write('<table>')

for data in self.data:
fout.write('<tr>')
fout.write('<td>%s</td>' % data['url'])
fout.write('<td>%s</td>' % data['title'].encode('utf-8'))
fout.write('<td>%s</td>' % data['summary'].encode('utf-8'))

fout.write('</tr>')

fout.write('</table>')
fout.write('</body>')
fout.write('</html>')

fout.close()</span>

内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理

标签：

相关文章推荐

新的分享

章节导航