首页手记 python下载奇书网的小说

python下载奇书网的小说

标签：

Python

网址为，奇书网
以前下载小说是爬取所有的章节，提取文章，构成小说，那样太慢，一本小说几千章节，好久才能下载一本，　现在找到一个有ＴＸＴ下载的地方，直接读写文章了．

准备按照首页，那边的栏目，下载玄幻奇幻武侠仙侠女频言情现代都市历史军事游戏竞技科幻灵异美文同人剧本教程名著杂志１０个专题的小说
整个过程用到了不少东西

html=requests.get(url,headers=headers,verify=False).text
soup=BeautifulSoup(html,'lxml')
#按照标签查找
tag_a=soup.p
#获取属性
name = tag_p.name
title = tag_p.attrs.get('title')
title = tag_p.get('title')
title = tag_p['title']

find&&find_all查找

soup.find('a')
soup.find('a',title='hhh')
soup.find('a',id='')
soup.find('a',class_='')

去掉开头，结尾的字符，用strip()函数
分割字符串使用 split()函数，追加元素到ｌist中使用append()函数，如果需要把另外一个ｌｉｓｔ的元素一一追加到另外一个list需要使用extend函数

            html=get_html(url[i]).text
            #title=re.find(re0,html)[0]
            href=re.findall(re1,html)
            #print(href)
            infor=re.split(",",href[0])
            get_inf=[]
            #print(infor)
            for j in range(len(infor)):
                te=infor[j].strip("'").strip("'")
                get_inf.append(te)

    # 这里采用正则表达式，也可以使用　title=cont[i].get("title")
        text=re.findall(re0,str(cont[i]))
        title.extend(text)

注意,这里是坑，被坑了好一会
Python3的dictionary的keys(), values(), items()返回的都是迭代器，如果需要像Python2一样返回列表，只要传给list就行了：

   novel_path=list(novel_inf.keys())
   novel_url=list(novel_inf.values())

下载小说，准备使用map函数实现多线程，加快速度,
全局变量，在函数外，最开始地方定义，在函数中想改变其中，必须使用global，不然函数中会屏蔽其值
参考文献

相关ｃｏｄｅ

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Jun 16 22:36:52 2018

@author: dflx
"""

import requests
import os
import re
from bs4 import BeautifulSoup
import time
from multiprocessing.dummy import Pool as ThreadPool

def get_html(url):
    try:
        headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.90 Safari/537.36 2345Explorer/9.3.2.17331',}
        response=requests.get(url,headers=headers,verify=False)
        print(response.status_code)
        response.raise_for_status
        response.encoding=response.apparent_encoding
        #print(response.text)
        return response
    except Exception as e:
        print("has exception:",e)

name=[]
def get_url(url):
    html=get_html(url).text
    re0=r'title="(.*?)">'
    soup=BeautifulSoup(html,"lxml")
    cont=soup.find_all('a')
    title=[]
    global name
    href=[]
    print("length=",len(cont))
    print(type(cont[0]))
    for i in range(2,12): #[2,12]
        print(cont[i])
        name.append(cont[i].string)
    # 这里采用正则表达式，也可以使用　title=cont[i].get("title")
        text=re.findall(re0,str(cont[i]))
        title.extend(text)
    # print(cont[i].get("href"))
        url="https://www.qisuu.la"+cont[i].get("href")
        href.append(url)

    print("title length=",len(title),type(title[0]),title[0])
    print("name length=",len(name),type(name[0]),name[0])
    print("href length",len(href),type(href[0]),href[0])
    return href

def mkdir(name,path):
    print(name)
    for i in name:
        file=path+i
        if not os.path.exists(file):
            os.makedirs(file)
    print("makdie successful")

def getChapterUrl(url,page):
    chapturl=[]
    href=get_url(url)
    for url in href:
        for num in range(1,page+1):
            chapt=url+"index_"+str(num)+".html"
            chapturl.append(chapt)
    print("down page length=",len(chapturl),chapturl[0])
    return chapturl

def getdownloadUrl(url,page):
    novel_href=[]
    chapturl=getChapterUrl(url,page)
    for ul in chapturl:
        html=get_html(ul).text
        soup=BeautifulSoup(html,"lxml")
        soup_div=soup.find_all("ul")
        tag_div=soup_div[5]
        #print(len(soup_div),type(soup_div[0]),soup_div[5])
        soup2=BeautifulSoup(str(tag_div),"lxml")
        tag_a=soup2.find_all('a')
        #print(tag_a)
        flag=1
        #print(tag_a[0])
        for i in range(len(tag_a)):
            url="https://www.qisuu.la"+tag_a[i].get("href")
            if flag%2!=0:
                novel_href.append(url)
            flag+=1
    print("the length novrl-href ",len(novel_href),novel_href[0])
    return novel_href

def downAllUrl(url,page):
    url=getdownloadUrl(url,page)
    print("----lenth=",len(url))
    print(name)
    novel_dict={}
    path="/home/dflx/下载/novel/"
    re0=r'<h1>(.*?)</h1>'
    re1=r'<script type="text/javascript">get_down_url\((.*?)\);</script>'
    for i in range(len(url)):
        try:
            html=get_html(url[i]).text
            #title=re.find(re0,html)[0]
            href=re.findall(re1,html)
            #print(href)
            infor=re.split(",",href[0])
            get_inf=[]
            #print(infor)
            for j in range(len(infor)):
                te=infor[j].strip("'").strip("'")
                get_inf.append(te)
            print(get_inf)

        #获取小说的名字
            soup=BeautifulSoup(html,"lxml")
            title=soup.find("h1").string
            print(title)

            index=i//(15*page)
            print(name[index])
            road=path+name[index]+"/"+get_inf[2]+".txt"
            print(type(road),road)
            print(type(get_inf[1]),get_inf[1])
            t1=time.time()
            #download(get_inf[1],pase,get_inf[2])
            novel_dict[road]=get_inf[1]
            t2=time.time()
            print("download spend "+str(t1-t2))
        except Exception as e:
            print("has excepton continue ",e)
            continue
    print(len(novel_dict))
    return novel_dict

novel_inf={}          
def threadDownload(url,page):
    global novel_inf
    novel_inf=downAllUrl(url,page)
    novel_path=list(novel_inf.keys())
    novel_url=list(novel_inf.values())
    pool=ThreadPool(2)
    #print(novel_path)
    print(type(novel_path))

    # thread download novel
    t1=time.time()
    result=pool.map(download,novel_path)
    t2=time.time()
    print("download spend "+str(t1-t2))
    pool.close()
    pool.join()

def download(ur):
    path=ur
    url=novel_inf[ur]
    html=get_html(url)
    text=html.content
    with open(path,'wb') as f:
        f.write(text)
    print("download "+ur+"success")

def main():
    url="https://dzs.qisuu.la/txt/22617.txt"
    url0="https://www.qisuu.la/"
    path="/home/dflx/下载/novel/"
    #getdownloadUrl(url0,1)
    #name=[]
    #get_url(url0)
    #mkdir(name,path)
    #downAllUrl(url0,3)
    threadDownload(url0,2)