python抓取看kindle(kankindle.com)所有的电子书并下载-爬虫

更新：2016-12-07

kankindle.com官网改版了，这个版本已经无法下载了,新版本正在更新中…

写了一个python脚本下载看kindle(kankindle.com)的所有电子书，程序会自动下载首页部分13页的所有电子书，下载到ebook目录下，程序会检测是否下载过，程序更新时间是20160421

（大家没事还是别全下载了，下载下来也不一定会看，啥时候想看下载也一样）、

#!/usr/bin/env python
# coding=utf-8
#www.503error.com 
#20160421

from bs4 import BeautifulSoup

import urllib2
import socket
import re
import unicodedata
import os
from urwid.text_layout import trim_line

def download(url):
    print 'starting download %s' % url
    response=urllib2.urlopen(url,timeout=30)
    html_data=response.read()
    
    soup=BeautifulSoup(html_data)
    print 'start to analayse---------------'
    
    
    title_soup=soup.find_all(class_='yanshi_xiazai')
    name_soup = soup.find_all('h1')
    tag_a = title_soup[0].a.attrs['href']
    tag_name= title_soup[0].a.contents
    link_name = name_soup[0]
    link_name = str(link_name).replace("<h1>","").replace("</h1>","")
    #print tag_name[0]
    #print link_name
    
    
    filename = link_name+".mobi"
    filename = "ebook/"+filename
    print 'filename is :%s' % filename
    
    print "downloading with urllib2 %s" % tag_a
    if os.path.exists(filename):
        print 'already donwload ,ignore'
    else:
        try:
            f = urllib2.urlopen(tag_a,timeout=60)
            data = f.read()
            #print 'the data is %s'% data
            with open(filename, "wb") as code:
                code.write(data)
        except Exception,e:
            print e
def get_all_link(url):
    print 'Starting get all the list'
    response=urllib2.urlopen(url,timeout=30)
    html_data=response.read()
    #print html_data
    
    soup=BeautifulSoup(html_data)
    link_soup = soup.find_all('a')
    #print link_soup
   
    for each_link in link_soup:
        if re.search('view',str(each_link)):
            #print each_link
            print each_link
            print each_link.attrs['href']
            download(each_link.attrs['href'])
if __name__ == '__main__':
    for page in range(1,13):
        url = "http://kankindle.com/simple/page/3"+str(page)
        url = url.strip()
        print url
        get_all_link(url)

#!/usr/bin/env python

# coding=utf-8

#www.503error.com

#20160421

from bs4 import BeautifulSoup

import urllib2

import socket

import re

import unicodedata

import os

from urwid.text_layout import trim_line

def download(url):

print 'starting download %s' % url

response=urllib2.urlopen(url,timeout=30)

html_data=response.read()

soup=BeautifulSoup(html_data)

print 'start to analayse---------------'

title_soup=soup.find_all(class_='yanshi_xiazai')

name_soup = soup.find_all('h1')

tag_a = title_soup[0].a.attrs['href']

tag_name= title_soup[0].a.contents

link_name = name_soup[0]

link_name = str(link_name).replace("<h1>","").replace("</h1>","")

#print tag_name[0]

#print link_name

filename = link_name+".mobi"

filename = "ebook/"+filename

print 'filename is :%s' % filename

print "downloading with urllib2 %s" % tag_a

if os.path.exists(filename):

print 'already donwload ,ignore'

else:

try:

f = urllib2.urlopen(tag_a,timeout=60)

data = f.read()

#print 'the data is %s'% data

with open(filename, "wb") as code:

code.write(data)

except Exception,e:

print e

def get_all_link(url):

print 'Starting get all the list'

response=urllib2.urlopen(url,timeout=30)

html_data=response.read()

#print html_data

soup=BeautifulSoup(html_data)

link_soup = soup.find_all('a')

#print link_soup

for each_link in link_soup:

if re.search('view',str(each_link)):

#print each_link

print each_link

print each_link.attrs['href']

download(each_link.attrs['href'])

if __name__ == '__main__':

for page in range(1,13):

url = "http://kankindle.com/simple/page/3"+str(page)

url = url.strip()

print url

get_all_link(url)

About
Latest Posts

Zhiming Zhang

Senior devops at Appannie

一个奔跑在运维路上的胖子

Latest posts by Zhiming Zhang (see all)

aws eks node 自动化扩展工具 Karpenter - 8月 10, 2022
ReplicationController and ReplicaSet in Kubernetes - 12月 20, 2021
public key fingerprint - 5月 27, 2021

一	二	三	四	五	六	日
« 八
			1	2	3	4
5	6	7	8	9	10	11
12	13	14	15	16	17	18
19	20	21	22	23	24	25
26	27	28	29	30

熟悉Ansible,Docker,Zabbix,Python,Shell,Iptables的这么一个devops

python抓取看kindle(kankindle.com)所有的电子书并下载-爬虫

Zhiming Zhang

Latest posts by Zhiming Zhang (see all)

本文共 1 个回复

11是 2019/03/14 14:42