python之小说下载器version3.0

我想了一下,每个版本打包exe 意义不大,如果是最终版什么的打一个还行,所以暂时不打包了有需要的可以留言,我在打包.

这里使用了第三方库pyquery,安装方法见:1.0版本链接

在上一版本的基础上做个改进.主要是,增加推荐榜,支持模糊查询,交互方式有一定优化.如上图:

下面是代码:

[python]
# -*- coding:gbk -*-
'''''
file desc:novel downloader
author:kingviker
email:kingviker@163.com.kingviker88@gmail.com
date:2013-05-21
depends:python 2.7.4,pyquery
'''

import os,codecs,urllib,urllib2,sys
from pyquery import PyQuery as pq


searchUrl = 'http://www.dushuge.net/modules/article/search.php'
baseSavePath="E:/enovel/"

def searchTopList():
    html = pq(url="http://www.dushuge.net")
    searchTopA= html("#compZnNav").next().find("td").eq(0)("a")
    searchTopList = []
    for index in range(1,len(searchTopA)):
        searchTopList.append([searchTopA.eq(index).text(),searchTopA.eq(index).attr("href")])
    return searchTopList

def searchNovel(novelName):



    values = urllib.urlencode({'searchkey' : novelName,
              'searchtype' : 'articlename'})
    req = urllib2.Request(url=searchUrl,data=values)
    response = urllib2.urlopen(req)
    searchHtml_pq = pq(response.read())

    novelUrlHtml = searchHtml_pq("#content > .sf-mainbox > .head > h1 > a")
    #print novelUrlHtml
    if not novelUrlHtml :
        resultList = searchHtml_pq("#content > table > tr")
        if resultList:
            novelList = []
            for index in range(1,len(resultList)):
                novelTR = resultList.eq(index)
                novelA = novelTR("td").eq(0)("a")
                #print novelA.text(),novelA.attr("href")
                novelList.append([novelA.text(),novelA.attr("href")])
            return novelList
        else:
            return
    return (novelUrlHtml.eq(2).text(),novelUrlHtml.eq(2).attr("href"))

def analyzeNovel(url):
    print "开始分析章节信息..."
    #using pyquery to grub the webpage's content
    html_pq = pq(url=url)
    #print html_pq("div.book_article_texttable").find(".book_article_texttext")
    totalChapters = len(html_pq("div.book_article_texttable").find(".book_article_listtext").find("a"))
    print "总章节数:",totalChapters
    return totalChapters

def fetchDownloadLinks(url):
    #using to save pieces and chapter lists
    pieceList=[]
    chapterList=[]

    html_pq = pq(url=url)
    #find the first piece of the novel.
    piece = html_pq("div.book_article_texttable > div").eq(0)

    isPiece = True
    if piece.attr("class")=="book_article_texttitle":
        #get the current piece's text
        pieceList.append(piece.text())
        #print "piece Text:", piece
    else:
        isPiece = False
        pieceList.append("无")
    #scan out the piece and chapter lists
    nextPiece=False
    while nextPiece==False:
        if isPiece:
            chapterDiv = piece.next()
        else:
            isPiece = True
            chapterDiv = piece
        #print "章节div长度:",chapterDiv.length
        piece = chapterDiv
        if chapterDiv.length==0:
            pieceList.append(chapterList[:])
            del chapterList[:]
            nextPiece=True
        elif chapterDiv.attr("class")=="book_article_texttitle":
            pieceList.append(chapterList[:])
            del chapterList[:]
            pieceList.append(piece.text())

        else:
            chapterUrls = chapterDiv.find("a");
         &

补充：Web开发 , Python ,