简单的爬虫（适用于小白）

最新推荐文章于 2021-09-25 11:18:38 发布

Mr.郑

最新推荐文章于 2021-09-25 11:18:38 发布

阅读量385

点赞数

文章标签： python

现在我给大家一个简单爬虫程序

目标：从百度百科爬取关键词python的价值数据

版本：python3.0

以下是源程序

spider_main

import html_downloader
import html_outputer
import html_parser
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 == 100:
break

count = count + 1
except:
print('craw failed')

self.outputer.output_html()

if __name__ == "__main__":
root_url = "https://baike.baidu.com/item/Python/407313"
obj_spider = SpiderMain()

obj_spider.craw(root_url)

html_downloader

import urllib.request

class HtmlDownloader(object):
def download(self,url):
if url is None:
return None

response = urllib.request.urlopen(url)

if response.getcode() != 200:
return None

return response.read()

html_outputer

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.htm', 'w')

fout.write('<html>')
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'].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()

html_parser

import re
import urllib.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/*"))
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 = { }

#url
res_data['url'] = page_url

#<dd class="lemmaWgt-lemmaTitle-title"> <h1>Python</h1>
title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")
if title_node is None:
return
res_data['title'] = title_node.get_text()
# <div class="lemma-summary">
summary_node = soup.find('div',class_="lemma-summary")
if summary_node is None:
return
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

url_manager

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

共五个模块