Python-利用beautifulsoup写个豆瓣热门图书爬虫

　　Anaconda3里边自带了bs4的包，省的我自己安装了。

　　最近觉得模块化的写法可以让代码变得清晰易读。而且随着代码的增多，找bug也会更方便。（目前我还写不出这么多）而且模块化有种工具化的思想，拿来主义的思想在里面，使用工具可是人等少数智慧动物的专利啊。之后也要多学习使用[try - except]的写法，可以直观的看出错误。

　　初学网页爬虫，目前只会爬取豆瓣这样清晰好看的静态网页，对于复杂的js控制的动态网页，我现在还束手无策。

# -*- coding: utf-8 -*-
"""
Created on Tue Jan  2 17:44:30 2018

@author: xglc
找到豆瓣图书的【新书速递】内容
"""
import requests
from bs4 import BeautifulSoup

def _gethtml():
    try:
        req = requests.get('https://book.douban.com/')
        data1 = []
        data1.append(req.text)
    except Exception as e:  
        raise e 
    return data1

def _getdata(html):
    title = []
    author = []
    data2 = {}
    soup = BeautifulSoup(html,'html.parser')
    for li in soup.find('ul',attrs={'class':'list-col list-col5 list-express slide-item'}).find_all("li"):
        title.append(li.find('div',class_='info').find('div',class_='title').text)
        author.append(li.find('div',class_='info').find('div',class_='author').text)
    data2['title'] = title
    data2['author'] = author
#    print (data2)
    return data2

def _txt(data3):
    with open('f://book.txt','w') as f:
        for title in data['title']:
            f.write(title)
        f.close
        
if __name__ == '__main__':  
    htmls = _gethtml()  
    data = _getdata(htmls[0])
    _txt(data)
#    print (data['title'])