简单爬虫——爬取百度百科总结
在慕课网学习简单爬虫来爬取百度百科的总结：
一、逻辑：根据根url: http://baike.baidu.com/item/Python,通过python的第三方插件Beautiful Soup来获取页面的html代码，找到我们需要的信息，这里我们需要的信息是：
#Python
和
# 中的h1标签、类名为lemma-summary的div内的内容。
有一个url管理器，来获取和管理所有需要爬取的链接a，比如在这里我们先获取http://baike.baidu.com/item/Python这个页面的所有a标签，将其存入一个容器（new_urls）中，然后依次爬取这个容器中的所有url，每爬一次，把爬取过的url从这个容器中删去，加入到old_urls容器中, 并且加入到new_urls时要判断这个url是否在new_urls和old_urls已经存在，若存在，不加入，防止重复爬取。然后通过页面下载器利用urllib2下载我们需要的页面代码，页面解析器html_parse利用beautifulsoup获取我们需要的数据。
二、具体代码：
1.主函数 spider_main.py
#_*_coding:utf-8_*_
from baike_spider2 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.HtmlPsrser()
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__":
# 爬虫入口页面
root_url = 'http://baike.baidu.com/item/Python'
obj_spider = SpiderMain()
# 启动爬虫
obj_spider.craw(root_url)
2.页面下载器 html_downloader.py
#_*_coding:utf-8_*_
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()
3.页面输出器 html_outputer.py
#_*_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("")
for data in self.datas:
fout.write("")
fout.write("%s " % data['url'].encode('utf-8'))
fout.write("%s " % data['title'].encode('utf-8'))
fout.write("%s " % data['summary'].encode('utf-8'))
fout.write(" ")
fout.write("
")
fout.write("")
fout.write("")
4.页面解析器 html_parser.py
#_*_coding:utf-8_*_
from bs4 import BeautifulSoup
import urlparse
import re
class HtmlPsrser(object):
def _get_new_urls(self, page_url, soup):
new_urls = set()
# links = soup.find_all('a', href=re.compile(r"/item/\d+\.html"))
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()
#
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.url管理器 url_manager.py
#_*_coding:utf-8_*_
class UrlManager(object):
def __init__(self):
self.new_urls = set()
self.old_urls = set()
#向管理器中添加新的url
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)
#向管理器中添加批量的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)
#判断管理器中是否有新的url
def has_new_url(self):
return len(self.new_urls) != 0
#获取新的带爬取的url
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
备注：
1.urljoin是拼接url地址的方法，比如 urljoin("http://www.asite.com/folder/currentpage.html", "anotherpage.html") 会输出'http://www.asite.com/folder/anotherpage.html'
urljoin("http://www.asite.com/folder/currentpage.html", "folder2/anotherpage.html")会输出'http://www.asite.com/folder/folder2/anotherpage.html'
urljoin("http://www.asite.com/folder/currentpage.html", "/folder3/anotherpage.html") 会输出'http://www.asite.com/folder3/anotherpage.html'
urljoin("http://www.asite.com/folder/currentpage.html", "../finalpage.html")会输出'http://www.asite.com/finalpage.html'
2.pop() 函数用于移除列表中的一个元素（默认最后一个元素），并且返回该元素的值
3.页面内容随时可能变化，根据不同情况做不同的分析处理，比如以前a标签的href跟现在的不一样，是类似于：/item/123.htm格式，所以在以前，页面解析器找a的代码为
# links = soup.find_all('a', href=re.compile(r"/item/\d+\.html"))