您的位置：首页 > 编程语言 > Python开发

Python2.7爬虫练习爬百度百科python词条

2016-04-22 23:57 316 查看

Eclipse New Project | New PyDev Package | New PyDev Module
Project:0418

Package:SpiderTest

Module: 5个模块，spider_main爬虫入口，=》 url_manager URL管理器， =》html_downloader 类似C#的HttpWebRequest请求获取html响应，=》 html_parser 类似HtmlAgilityPack的数据分析，=》 html_outputer 输出到文件

1.spider_main

# coding:utf8
from baike_spider import url_manager, html_downloader, html_parser, html_outputer

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 == 100:
break

count = count + 1
except:
print("craw fail")

self.outputer.output_html()

if __name__ == "__main__":
root_url = "http://baike.baidu.com/view/21087.htm"
obj_spider = SpiderMain()
obj_spider.craw(root_url)

2.url_manager

# 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

3.html_downloader

# 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()

4.html_parser

# coding:utf8

from bs4 import BeautifulSoup
import re
import urlparse

class HtmlParser(object):

def _get_new_urls(self, page_url, soup):
new_urls = set()
#  /view/123.htm
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
#  <dl class="lemmaWgt-lemmaTitle lemmaWgt-lemmaTitle-"><h1>Python</h1><dd class="lemmaWgt-lemmaTitle-title">
title_node = soup.find('dl',class_="lemmaWgt-lemmaTitle lemmaWgt-lemmaTitle-").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

5.html_outputer

# coding:utf-8

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("<html>")
fout.write("<body>")
fout.write("<table>")
for data in self.datas:
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()

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