小爬糗事百科

首先分析糗百页面：

目标是获取文字内容和文章链接ID，并保存到文件。

#!/usr/bin/env/python
#coding:utf-8

if __name__ == '__main__':
	from  urllib import request,parse
	import re

	#抓取,获取源代码
	url='https://www.qiushibaike.com/textnew/'
	headers={
	"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36"
	}
	req=request.Request(url,headers=headers)
	resp=request.urlopen(req)
	html=resp.read().decode('utf-8')
	if resp.getcode()!=200:
		print('url open failed!')
	
	#解析数据
	pattern_id=re.compile(r'<a href="/article/(\d+)".*class=.contentHerf. >')
	pattern_content=re.compile(r'<div class="content">.*?<span>(.*?)</span>',re.S)

	ids=re.findall(pattern_id,html)
	contents=re.findall(pattern_content,html)
	data={}
	for i in range(len(ids)):
		pattern=r'<br/>'
		content=re.sub(pattern,'\n', contents[i])
		data[ids[i]]=content
	
	#保存数据
	directory='spider_qiubai/'
	for key in data.keys():
		f=open(directory+key+'.txt','w')
		try:
			f.write(data[key])
		except Exception as e:
			print("write file "+key+" failed! "+e)
		else:
			print("write file "+key+" successfully!")
		finally:
			f.close()

　　运行结果：

转载于:https://www.cnblogs.com/jasonhaven/p/7375503.html