在pydev,先设置utf-8
windows,preference,general,workspace,text file coding–>utf-8
windows,preference,general,editor,text editors,spelling,encoding–>utf-8
主程序spider_main.py
#coding:UTF8
from baike_spider import url_manager, html_downloader, html_parser, \
html_outputer
class SpiderMain(object):
def __init__(self):#构造函数,初始化所需要的对象
self.urls = url_manager.UrlManager()#url管理器
self.downloader = html_downloader.HtmlDownloader()#html下载器
self.parser = html_parser.HtmlParser()#html解析器
self.outputer = html_outputer.HtmlOutputer()#html输出器
def craw(self, root_url):
#当前第几个url
count = 1
#把入口url添加进url管理器(待爬取的url列表)
self.urls.add_new_url(root_url)
#当url列表中含有待爬取的url时
while(self.urls.has_new_url()):
try:
#从待爬取的url列表中获取一个url
new_url = self.urls.get_new_url()
#打印序号以及url地址
print ('craw %d : %s' % (count, new_url))
count = count + 1
#下载url对应的html页面
html_cont = self.downloader.download(new_url)
#解析html,获得新的url列表和数据
new_urls, new_data = self.parser.parse(new_url, html_cont)
#把新的url列表添加到待爬取的url列表
self.urls.add_new_urls(new_urls)
#收集数据
self.outputer.collect_data(new_data)
#打印至多1000个页面
if(count == 10):
break
except:#爬取失败时执行
print ('craw failed')
#输出收集到的全部数据
self.outputer.output_html()
if(__name__ == "__main__"):
root_url = "https://baike.baidu.com/item/Python/407313"
obj_spider = SpiderMain()
obj_spider.craw(root_url)
url管理器url_manager.py
#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
html下载器html_downloader.py
#coding:UTF8
from urllib import request
class HtmlDownloader(object):
def download(self, url):
if(url is None):
return None
response = request.urlopen(url)
if(response.getcode() != 200):
return None
return response.read().decode('utf8')
html解析器html_parser.py
#coding:UTF8
import re
from urllib import parse
from bs4 import BeautifulSoup
class HtmlParser(object):
def _get_new_urls(self, page_url, soup):
new_urls = set()
links = soup.find_all('a', href = re.compile(r'/item/\w+'))
for link in links:
new_url = link['href']
new_full_url = parse.urljoin(page_url, new_url)
#把完整的url添加到待爬取的url列表
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
#<div id="baike-title"> <h1> <span class="title">
title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find('h1')
res_data['title'] = title_node.get_text()
#<div class="card_content" id="js-card-content">
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')
new_urls = self._get_new_urls(page_url, soup)
new_data = self._get_new_data(page_url, soup)
return new_urls, new_data
html输出器html_outputer.py
#coding:UTF8
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>")
#ascii
for data in self.datas:
fout.write("<tr>")
fout.write("<td>%s</td>" % data['url'])
fout.write("<td>%s</td>" % data['title'].replace(u'\xa0', u' '))
fout.write("<td>%s</td>" % data['summary'].replace(u'\xa0', u' '))
fout.write("</tr>")
fout.write('</table>')
fout.write("</body>")
fout.write("</html>")