python简单爬虫代码示例

目标网站：http://www.jueshitangmen.info/tian-meng-bing-can-15.html
代码：
from urllib.request import urlopen
from bs4 import BeautifulSoup

html1=urlopen(“http://www.jueshitangmen.info/tian-meng-bing-can-15.html”).read() #获取二进制文件
html2=html1.decode(“utf-8”)#把二进制转为string类型
f = open(‘news.html’,‘w’,encoding=‘utf-8’)
f.write(newshtml2)
f.close()
#print(type(html1))
#print(type(html2))
#print(("\n" in html2))#换行符是包括在网页字符串里面的
#print(html2)
b_soup=BeautifulSoup(html2,features=“lxml”)#class 'bs4.BeautifulSoup
all_p=b_soup.find_all(“p”)#<class ‘bs4.element.ResultSet’>
#print(all_p[0])
f = open(‘story_p.html’,‘w’,encoding=‘utf-8’)
f.close()
for i in all_p:
f = open(‘story_p.html’,‘a’,encoding=‘utf-8’)
f.write(" “+i.get_text()+”\n")
f.close()
print(type(i.get_text()))

#print(type(all_p))
#print(b_soup)
#print(type(b_soup))