Python爬虫实现爬取百度百科词条功能实例
马哥Linux运维
共 5438字,需浏览 11分钟
·
2021-09-06 15:27
本文实例讲述了Python爬虫实现爬取百度百科词条功能。分享给大家供大家参考,具体如下:
以下我写了一个爬取百度百科词条的实例。
爬虫主程序入口
from crawler_test.html_downloader import UrlDownLoader
from crawler_test.html_outer import HtmlOuter
from crawler_test.html_parser import HtmlParser
from crawler_test.url_manager import UrlManager
# 爬虫主程序入口
class MainCrawler():
def __init__(self):
# 初始值,实例化四大处理器:url管理器,下载器,解析器,输出器
self.urls = UrlManager()
self.downloader = UrlDownLoader()
self.parser = HtmlParser()
self.outer = HtmlOuter()
# 开始爬虫方法
def start_craw(self, main_url):
print('爬虫开始...')
count = 1
self.urls.add_new_url(main_url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
print('爬虫%d,%s' % (count, new_url))
html_cont = self.downloader.down_load(new_url)
new_urls, new_data = self.parser.parse(new_url, html_cont)
# 将解析出的url放入url管理器,解析出的数据放入输出器中
self.urls.add_new_urls(new_urls)
self.outer.conllect_data(new_data)
if count >= 10:# 控制爬取的数量
break
count += 1
except:
print('爬虫失败一条')
self.outer.output()
print('爬虫结束。')
if __name__ == '__main__':
main_url = 'https://baike.baidu.com/item/Python/407313'
mc = MainCrawler()
mc.start_craw(main_url)
URL管理器
# URL管理器
class UrlManager():
def __init__(self):
self.new_urls = set() # 待爬取
self.old_urls = set() # 已爬取
# 添加一个新的url
def add_new_url(self, url):
if url is None:
return
elif url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
# 批量添加url
def add_new_urls(self, urls):
if urls is None or len(urls) == 0:
return
else:
for url in urls:
self.add_new_url(url)
# 判断是否有url
def has_new_url(self):
return len(self.new_urls) != 0
# 从待爬取的集合中获取一个url
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
网页下载器
from urllib import request
# 网页下载器
class UrlDownLoader():
def down_load(self, url):
if url is None:
return None
else:
rt = request.Request(url=url, method='GET') # 发GET请求
with request.urlopen(rt) as rp: # 打开网页
if rp.status != 200:
return None
else:
return rp.read() # 读取网页内容
网页解析器
import re
from urllib import parse
from bs4 import BeautifulSoup
# 网页解析器,使用BeautifulSoup
class HtmlParser():
# 每个词条中,可以有多个超链接
# main_url指url公共部分,如“https://baike.baidu.com/”
def _get_new_url(self, main_url, soup):
# baike.baidu.com/
# <a target="_blank" href="/item/%E8%AE%A1%E7%AE%97%E6%9C%BA%E7%A8%8B%E5%BA%8F%E8%AE%BE%E8%AE%A1%E8%AF%AD%E8%A8%80" rel="external nofollow" >计算机程序设计语言</a>
new_urls = set()
# 解析出main_url之后的url部分
child_urls = soup.find_all('a', href=re.compile(r'/item/(\%\w{2})+'))
for child_url in child_urls:
new_url = child_url['href']
# 再拼接成完整的url
full_url = parse.urljoin(main_url, new_url)
new_urls.add(full_url)
return new_urls
# 每个词条中,只有一个描述内容,解析出数据(词条,内容)
def _get_new_data(self, main_url, soup):
new_datas = {}
new_datas['url'] = main_url
# <dd class="lemmaWgt-lemmaTitle-title"><h1>计算机程序设计语言</h1>...
new_datas['title'] = soup.find('dd', class_='lemmaWgt-lemmaTitle-title').find('h1').get_text()
# class="lemma-summary" label-module="lemmaSummary"...
new_datas['content'] = soup.find('div', attrs={'label-module': 'lemmaSummary'},
class_='lemma-summary').get_text()
return new_datas
# 解析出url和数据(词条,内容)
def parse(self, main_url, html_cont):
if main_url is None or html_cont is None:
return
soup = BeautifulSoup(html_cont, 'lxml', from_encoding='utf-8')
new_url = self._get_new_url(main_url, soup)
new_data = self._get_new_data(main_url, soup)
return new_url, new_data
输出处理器
# 输出器
class HtmlOuter():
def __init__(self):
self.datas = []
# 先收集数据
def conllect_data(self, data):
if data is None:
return
self.datas.append(data)
return self.datas
# 输出为HTML
def output(self, file='output_html.html'):
with open(file, 'w', encoding='utf-8') as fh:
fh.write('<html>')
fh.write('<head>')
fh.write('<meta charset="utf-8"></meta>')
fh.write('<title>爬虫数据结果</title>')
fh.write('</head>')
fh.write('<body>')
fh.write(
'<table style="border-collapse:collapse; border:1px solid gray; width:80%; word-break:break-all; margin:20px auto;">')
fh.write('<tr>')
fh.write('<th style="border:1px solid black; width:35%;">URL</th>')
fh.write('<th style="border:1px solid black; width:15%;">词条</th>')
fh.write('<th style="border:1px solid black; width:50%;">内容</th>')
fh.write('</tr>')
for data in self.datas:
fh.write('<tr>')
fh.write('<td style="border:1px solid black">{0}</td>'.format(data['url']))
fh.write('<td style="border:1px solid black">{0}</td>'.format(data['title']))
fh.write('<td style="border:1px solid black">{0}</td>'.format(data['content']))
fh.write('</tr>')
fh.write('</table>')
fh.write('</body>')
fh.write('</html>')
效果(部分):
原文链接:https://www.cnblogs.com/wcwnina/p/8619084.html
文章转载:Python编程学习圈
(版权归原作者所有,侵删)
点击下方“阅读原文”查看更多
评论