通过学习imooc网上的教程，自己实现了python 的简单爬虫程序（爬取百度百科上的 python页面的一百个链接以及其中的title和summary）
组成爬虫的关键模块包括URL管理器，HTML下载器，和HTML解析器
在前期需要找到数据的抓取策略，从html文件中找到所需要的数据，以及数据的特征，利用正则表达式来匹配。
main.py
from baike import html_downloader
from baike import html_outputer
from baike import html_parser
from baike 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 ', count, ':', new_url)
#print(new_url)
html_cont = self.downloader.download(new_url)
#print(html_cont)
new_urls, new_data = self.parser.parse(new_url, html_cont)
#print(new_data)
self.urls.add_new_urls(new_urls)
self.outputer.collect_data(new_data)
if count == 100:
break
count = count + 1
except:
print("craw failed")
self.outputer.output_html()
if __name__ == "__main__":
root_url = "http://baike.baidu.com/item/Python"
obj_spider = SpiderMain()
obj_spider.craw(root_url)from bs4 import BeautifulSoup
import re
import urllib.parse
class HtmlParser(object):
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
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 = urllib.parse.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
#<dd class="lemmaWgt-lemmaTitle-title"><h1>Python</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
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', encoding='utf-8')
fout.write("<html>")
fout.write("<head><meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\"></head>")
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'])
fout.write("<td>%s</td>" % data['summary'])
fout.write("</tr>")
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")html_parser.py
from bs4 import BeautifulSoup
import re
import urllib.parse
class HtmlParser(object):
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
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 = urllib.parse.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
#<dd class="lemmaWgt-lemmaTitle-title"><h1>Python</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
url_manager.py
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
fout.write("<head><meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\"></head>")
941
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
