简介
爬虫是一段自动抓取互联网信息的程序。它的价值是互联网数据为我所有。利用爬取到的数据，可以做很多的事情如：可以进行数据统计，对比；可以利用爬取的数据做某一方面的app；也可以利用爬取的数据做一个新闻阅读器等等。
爬虫架构
1）url管理器 2）网页下载器 3）网页分析器 4）爬虫调用器 5）价值数据使用
爬虫实现
1）调度器实现
# 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)
2）url管理器实现
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）url下载器实现
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）url解析器实现
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(‘p’, 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）价值数据输出显示
# 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(“”)
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()
执行
本爬虫为爬取百度百科与python关键字相关的1000个静态网页，对网页中的数据，主要提取关键词和摘要信息，并将爬取的信息以html文件的方式存储，之后利用浏览器打开即可实现访问。