python下载神通板砖有声版

背景

前端时间在喜马拉雅上偶然听到牛大宝说的有声小说神通板砖，说的很是幽默，听的正起劲的时候开始收费了，于是我就在网上找了下看看有没有免费版，一搜果然有，但该网站上广告太多了，于是我就写了个小脚本可以批量下载的，供大家学习，如果您使用该脚本用于任何非法用途，均与本站无关。

思路

1. 找到可以免费下载资源网站
2. 针对该网站html进行分析并编写下载脚本
3. linux命令行自动顺序播放

实施

找到可以免费下载资源网站

网址： www.ting56.com/mp3/6475.html#liebiao

编写脚本 stbz.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from html.parser import HTMLParser
import urllib3
import os

http = urllib3.PoolManager()
baseUrl='http://www.ting56.com'

class Mp3HTMLParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)

    def handle_starttag(self,tag,attrs):
        if tag == 'div':
            for (k,v) in attrs:
                if k=='id' and v=='bofangqi':
                    print(tag)

class MyHTMLParser(HTMLParser):

    def __init__(self):
        self.a_t = False
        HTMLParser.__init__(self)

    def handle_starttag(self, tag, attrs):
        """
        recognize start tag, like <div>
        :param tag:
        :param attrs:
        :return:
        """
        if tag == 'div':
            for (k,v) in attrs:
                if k == 'id' and v == 'vlink_1':
                    self.a_t = True
                    #print("Encountered a start tag:", tag)
                else:
                    self.a_t = False
        if self.a_t:
            if tag == 'a':
                title = ''
                url = ''
                for (k,v) in attrs:
                    if k=='href':
                        url=baseUrl+v
                    if k=='title':
                        title=v
                #print('%s %s \n' % (title,url))
                download(title,url)
                #r = http.request('GET',url)
                #dataStr = r.data.decode('gbk')
                #parser = Mp3HTMLParser()
                #parser.feed(dataStr)

#    def handle_endtag(self, tag):
#        """
#        recognize end tag, like </div>
#        :param tag:
#        :return:
#        """
#        print("Encountered an end tag :", tag)
#
    def handle_data(self, data):
        """
        recognize data, html content string
        :param data:
        :return:
        """
        pass
        #if self.a_t:
            #print(data)
#
#    def handle_startendtag(self, tag, attrs):
#        """
#        recognize tag that without endtag, like <img />
#        :param tag:
#        :param attrs:
#        :return:
#        """
#        print("Encountered startendtag :", tag)
#
#    def handle_comment(self,data):
#        """
#
#        :param data:
#        :return:
#        """
#        print("Encountered comment :", data)

def fromCharCode(n):
    return chr(n%256)

def download(name,url):
    print('%s%s' % (name,url))
    cmd = 'echo "%s%s" >> /tmp/stbz/downloadList.txt' % (name,url)
    os.system(cmd)

    try:
        if int(name) <= 137:
            return
        r = http.request('GET',url)
        dataStr = r.data.decode('gbk')
        os.environ['htmlStr'] = dataStr
        cmd = 'echo $htmlStr | sed "s/.*FonHen_JieMa(\([0-9\\\'\*]*\)).*/\\1/g"'
        t = os.popen(cmd).read()
        t = t[1:-2]
        #print(t)
        tArr = t.split('*')
        tmp = ''
        for s in tArr:
            if len(s)==0:
                continue
            tmp = tmp + fromCharCode(int(s))
        print(tmp)
        datas = tmp.split('&')
        print(datas)
        cmd = 'curl %s --output /tmp/stbz/%s.%s' % (datas[0],name,datas[2])
        if os.system(cmd) != 0:
            raise Exception("download err")
    except:
        print('[err] %s%s ' % (name,url))
        cmd = 'echo "%s%s" >> /tmp/stbz/err.txt' % (name,url)
        os.system(cmd)

if __name__ == "__main__":
    os.system('echo "" > /tmp/stbz/downloadList.txt')
    r = http.request('GET','http://www.ting56.com/mp3/6475.html#liebiao')
    dataStr = r.data.decode('gbk')
    #print(dataStr)
    parser = MyHTMLParser()
    parser.feed(dataStr)

自动播放脚本

下载好的音频文件都是以数字编号的，所以可以播放完一个自动进行下一个，并且记录当前播放记录，方便下次继续播放 将下面的脚本保存为play.sh

#!/usr/bin/env bash

basepath=$(cd `dirname $0`;pwd)
cd $basepath
echo "workspace [$basepath]"

posfile="stbz.pos"

if [ ! -f "$posfile" ]; then
    echo '1.m4a' > ${posfile}
fi

pos=$(cat ${posfile})
state="start"

for name in `cat ./stbz.lst`;do
    if [ $state = "start" ]; then
        if [ $pos = $name ]; then
            echo "begin play ${pos}"
            mplayer $name 1>> /dev/null 2>>err.txt || exit 1
            state="play"
            echo "${name}" > ${posfile}
        fi
    else
        echo "begin play ${name}"
        echo "${name}" > ${posfile}
        mplayer $name 1>> /dev/null 2>>err.txt || exit 1
    fi
done

原文来自 https://www.h3blog.com/article/python-download-stbz/