python 入门-网络爬虫（小说下载）

总结：

<1>if __name__ == '__main__':
    target = 'http://www.biqukan.com/1_1094/5403177.html'
    req = requests.get(url=target)
    req.encoding = req.apparent_encoding
    print(req.text)

<2>python 本地安装 beautifulsoup方法！
（1）
1、在python官网找到beautifulsoup模块的下载页面，点击"downloap"将该模块的安装包下载到本地
2、将该安装包解压，然后在打开cmd，并通过cmd进入到该安装包解压后的文件夹目录下
3、在该文件目录下输入"python setup.py install"，进行beautilfulsoup4模块的安装，当安装完成后会看到有"Finished"字样
4、安装完成后，在cmd中运行Python,然后输入"form bs4 import BeautilfulSoup" 导入该模块，如果成功安装的话将没有任何打印信息，否则会有相应的错误信息打印
（2）
$wget http://www.crummy.com/software/BeautifulSoup/bs4/download/4.3/beautifulsoup4-4.3.2.tar.gz
$tar zxvf beautifulsoup4-4.3.2.tar.gz
$cd beautifulsoup4-4.3.2
$python setup.py install
$python
>> from bs4 import BeautifulSoup
（3）
打开cmd，然后在cmd中输入命令“pip install beautilfulsoup4”，就可以成功安装beautilfulsoup4，不过该版本不一定会是4.4.1，版本会是当前python库中的最新版本。

<3>python 中tab 和四个空格 不 相等

<4> 小数转换位百分比
#方法一
a = 0.3214323
bb = "%.2f%%" % (a * 100)
print bb
# 输出结果是32.14%
#方法二
a = 0.3214323
b = str(a*100) + '%'
print b
# 输出结果是32.14323%

# 如果想保留小数点后两位
c = str(a)[:4]+ '%'
print c
# 输出结果是0.32%

比如将 0.1234 转化为 12.34% 的形式：
rate = 0.1234
print('%.2f%%' % (rate * 100))

说明：第一个百分号和 .2f 相连，表示浮点数类型保留小数点后两位格式化输出；然后的两个连续的%%，则最终会输出一个%号出来，有对%进行转义的含义；

 

小说下载代码：

#!usr/bin/env python

from bs4 import BeautifulSoup
import requests,sys

'''
if __name__ == '__main__':
    target = 'http://www.biqukan.com/1_1094/5403177.html'
    req = requests.get(url=target)
    req.encoding = req.apparent_encoding
    html = req.text
    bf = BeautifulSoup(html)
    texts = bf.find_all('div', class_ = 'showtxt')
 #   print(texts)
    print(texts[0].text.replace('\xa0'*8,'\n\n')) '''
	
'''	
if __name__ == "__main__":
    target = 'http://www.biqukan.com/1_1094/'
    req = requests.get(url = target)
    req.encoding = req.apparent_encoding
    html = req.text
    div_bf = BeautifulSoup(html)
    div = div_bf.find_all('div', class_ = 'listmain')
    print(div[0])'''

'''	
if __name__ == "__main__":
    server = 'http://www.biqukan.com/'
    target = 'http://www.biqukan.com/1_1094/'
    req = requests.get(url = target)
    req.encoding = req.apparent_encoding
    html = req.text
    div_bf = BeautifulSoup(html)
    div = div_bf.find_all('div', class_ = 'listmain')
    a_bf = BeautifulSoup(str(div[0]))
    a = a_bf.find_all('a')
    for each in a:
        print(each.string, server + each.get('href'))'''	
		

''' readme download yi-nian-yong-heng '''
class downloader(object):

    def __init__(self):
        self.server = 'http://www.biqukan.com/'
        self.target = 'http://www.biqukan.com/1_1094/'
        self.names = []           
        self.urls = []          
        self.nums = 0          

    '''get_download_url '''  
    def get_download_url(self):
        req = requests.get(url = self.target)
        req.encoding = req.apparent_encoding
        html = req.text
        div_bf = BeautifulSoup(html,"html.parser")
        div = div_bf.find_all('div', class_ = 'listmain')
        a_bf = BeautifulSoup(str(div[0]),"html.parser")
        a = a_bf.find_all('a')
        self.nums = len(a[5:10])                                
        for each in a[5:10]:
            self.names.append(each.string)
            self.urls.append(self.server + each.get('href'))

    ''' get_contents per chapter'''
    def get_contents(self, target):
        req = requests.get(url = target)
        req.encoding = req.apparent_encoding
        html = req.text
        bf = BeautifulSoup(html,"html.parser")
        texts = bf.find_all('div', class_ = 'showtxt')
        texts = texts[0].text.replace('\xa0'*8,'\n\n')
        return texts

    ''' dolad to local'''
    def writer(self, name, path, text):
        write_flag = True
        with open(path, 'a', encoding='utf-8') as f:
            f.write(name + '\n')
            f.writelines(text)
            f.write('\n\n')

if __name__ == "__main__":
    dl = downloader()
    dl.get_download_url()
    txt = "      download begin tatal {} chapters"
    print(txt.format(dl.nums))
    for i in range(dl.nums):
        dl.writer(dl.names[i], 'my.txt', dl.get_contents(dl.urls[i]))
        sys.stdout.write(" download:%.3f%%" %  float(i/dl.nums*100) + '\r')
        sys.stdout.flush()
    print('      download  end')