python爬虫主要就是五个模块:爬虫启动入口模块,URL管理器存放已经爬虫的URL和待爬虫URL列表,html下载器,html解析器,html输出器 同时可以掌握到urllib2的使用、bs4(BeautifulSoup)页面解析器、re正则表达式、urlparse、python基础知识回顾(set集合操作)等相关内容。

本次python爬虫百步百科,里面详细分析了爬虫的步骤,对每一步代码都有详细的注释说明,可通过本案例掌握python爬虫的特点:

1、爬虫调度入口(crawler_main.py)

# coding:utf-8
from com.wenhy.crawler_baidu_baike import url_manager, html_downloader, html_parser, html_outputer

print "爬虫百度百科调度入口"

# 创建爬虫类
class SpiderMain(object):

# 初始化 url管理器 html下载器 解析器 输出器
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.output = html_outputer.HtmlOutput()


def craw(urls, downloader, parser, output, root_url):
# 计数
count = 1
# 添加url到url管理器中
urls.add_new_url(root_url)
# 判断是否有新的URL
while urls.has_new_url():
try:

# 获取新的URL
new_url = urls.get_new_url()
print 'crawler %d : %s' % (count, new_url)
# 下载html页面数据
html_cont = downloader.download(new_url)
# 解析页面得到新的url列表,新的数据
new_urls, new_data = parser.parser(new_url, html_cont)
# 把解析到的url数组批量添加到url管理器中
urls.add_new_urls(new_urls)
# 收集数据
output.collect_data(new_data)
# 爬虫1000页面
if count == 500:
break
count = count + 1

except Exception as e:
print 'Crawler Failed ', e

output.output_html()


if __name__ == '__main__':
# 入口URL 百度百科地址
root_url = "http://baike.baidu.com/item/Python"
# 创建爬虫
obj_spider = SpiderMain()
# 启动爬虫
craw(obj_spider.urls, obj_spider.downloader, obj_spider.parser, obj_spider.output, root_url)

2、封装URL管理器(url_manager.py)
# coding:utf-8

print "URL管理器"


class UrlManager(object):

# 初始化url容器(set集合)
def __init__(self):
self.new_urls = set()
self.old_urls = set()

# 添加一个新的待爬取url
def add_new_url(self, url):

if url is None:
return

# 判断url不在新的url集合中也不再旧的url集合中 说明是一个全新的url
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)

# 批量添加解析页面的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)

# 判断是否有新的待爬取的url
def has_new_url(self):
# 如果新的url集合里面len不等于0 说明有待爬取的url
return len(self.new_urls) != 0

# 获得url地址
def get_new_url(self):
# 获取url并移除当前url
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url

3、HTML下载器(html_downloader.py)
# coding:utf-8

import urllib2
print "下载HTML"


class HtmlDownloader(object):

def download(self, url):
# 判断是否为空
if url is None:
return None
# 下载url
response = urllib2.urlopen(url)
# 判断返回结果是否为200
if response.getcode() != 200:
return None
# 成功 返回页面内容
return response.read()

4、HTML 解析器(html_parser.py)
# coding:utf-8

from bs4 import BeautifulSoup
import re
import urlparse

print "HTML 解析器"


class HtmlParser(object):

def _get_new_urls(self, page_url, soup):

# 创建一个集合保存页面解析出来的所有url
new_urls = set()
# /item/ 词条url
links = soup.find_all('a', href=re.compile(r'/item/'))
for link in links:
# 获取连接
new_url = link['href']
# url拼接
new_full_url = urlparse.urljoin(page_url, new_url)
# print 'new_full_url', new_full_url
# 添加到集合中url
new_urls.add(new_full_url)
return new_urls


def _get_new_data(self, page_url, soup):
# 定义一个dict 集合
res_data = {}

res_data['url'] = page_url
# < dd class ="lemmaWgt-lemmaTitle-title" >< h1 > 自由软件 < / 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


# 解析器
def parser(self, page_url, html_content):

if page_url is None or html_content is None:
return

# 使用BeautifulSoup 解析html页面
soup = BeautifulSoup(html_content, '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 输出页面(html_outputer.py)
# coding:utf-8

print "HTML 输出页面"


class HtmlOutput(object):

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

# 收集数据
def collect_data(self, data):
if data is None:
return
self.datas.append(data)

# 展示数据
def output_html(self):

fout = open('output.html', 'w')

fout.write('<html>')
fout.write('<head>')
fout.write('<meta http-equiv="Content-Type" content="text/html;charset=utf-8">')
fout.write('</head>')
fout.write('<body>')
fout.write('<table border="1">')
for data in self.datas:
fout.write('<tr>')
fout.write('<td><a href = "%s">%s</a></td>' % (data['url'].encode('utf-8'), 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()


总结:python爬虫主要就是五个模块:爬虫启动入口模块,URL管理器存放已经爬虫的URL和待爬虫URL列表,html下载器,html解析器,html输出器
同时可以掌握到urllib2的使用、bs4(BeautifulSoup)页面解析器、re正则表达式、urlparse、python基础知识回顾(set集合操作)等相关内容。

posted @ 2017-07-12 20:21  Java/Python  阅读(1319)  评论(0编辑  收藏  举报