本文是为了防止自己以后忘了,小白可以参考,大神请绕道~
先来扫盲,什么是爬虫:爬虫就是一系列按照某种规则自动从网上爬取信息的代码或者脚本。
本文代码功能:从百度百科里面爬取20个和python相关的词条的链接,标题及内容(代码来自于慕课网视频,自己看完视频写了一遍,做了部分更改:将Python2变成python3;更新链接的提取方式,视频里的用不了了。应该也算是原创了,感兴趣的同学请戳https://www.imooc.com/video/10694)。
爬虫代码分为五个模块,分为爬虫调度器,url 管理器,html下载器,html解析器,html输出器。
首先是调度器:负责掌控整个爬取过程
import html_downloader
import html_outputer
import html_parser
import url_manager
class SipderMain(object):
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDowner()
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 {} : {}'.format(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_date(new_data)
if count == 20:
break
count += 1
except:
print('craw failed')
self.outputer.output_html()
if __name__ == '__main__':
root_url = r'https://baike.baidu.com/item/Python/407313?fr=aladdin'
obj_spider = SipderMain()
obj_spider.craw(root_url)
然后是url管理器:负责管理url,添加、判断、获取url
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
然后是html下载器:负责读取html内容
import urllib.request
class HtmlDowner(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()
然后是htm解析器:负责解析html内容
import re
from urllib.parse import urljoin
from bs4 import BeautifulSoup
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()
#<a href="#2">下载Python</a>
links = soup.find_all('a', href=re.compile('/item/*'))
for link in links:
new_url = link['href']
new_full_url = 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
最后是html输出器:负责将爬取到的结果格式化输出
class HtmlOutputer(object):
def __init__(self):
self.datas = []
def collect_date(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('<body>')
fout.write('<table>')
for data in self.datas:
fout.write('<tr>')
fout.write('<td> {} </td>'.format(data['url']))
fout.write('<td> {} </td>'.format(data['title']))
fout.write('<td> {} </td>'.format(data['summary']))
fout.write('</tr>')
fout.write('</table>')
fout.write('</body>')
fout.write('</html>')
fout.close()
最后的结果就是这样子: