使用python采集脚本之家电子书资源并自动下载到本地的实例脚本

jb51上面的资源还比较全，就准备用python来实现自动采集信息，与下载啦。

Python具有丰富和强大的库，使用urllib，re等就可以轻松开发出一个网络信息采集器！

下面，是我写的一个实例脚本，用来采集某技术网站的特定栏目的所有电子书资源，并下载到本地保存！

软件运行截图如下：

在脚本运行时期，不但会打印出信息到shell窗口，还会保存日志到txt文件，记录采集到的页面地址，书籍的名称，大小，服务器本地下载地址以及百度网盘的下载地址！

实例采集并下载武林站长站的python栏目电子书资源：

# -*- coding:utf-8 -*-import reimport urllib2import urllibimport sysimport osreload(sys)sys.setdefaultencoding('utf-8')def getHtml(url): request = urllib2.Request(url) page = urllib2.urlopen(request) htmlcontent = page.read() #解决中文乱码问题 htmlcontent = htmlcontent.decode('gbk', 'ignore').encode("utf8",'ignore') return htmlcontentdef report(count, blockSize, totalSize): percent = int(count*blockSize*100/totalSize) sys.stdout.write("r%d%%" % percent + ' complete') sys.stdout.flush()def getBookInfo(url): htmlcontent = getHtml(url); #print "htmlcontent=",htmlcontent; # you should see the ouput html #<h1 class="h1user">crifan</h1> regex_title = '<h1s+?itemprop="name">(?P<title>.+?)</h1>'; title = re.search(regex_title, htmlcontent); if(title): title = title.group("title"); print "书籍名字:",title; file_object.write('书籍名字:'+title+'r'); #<li>书籍大小：<span itemprop="fileSize">27.2MB</span></li> filesize = re.search('<spans+?itemprop="fileSize">(?P<filesize>.+?)</span>', htmlcontent); if(filesize): filesize = filesize.group("filesize"); print "文件大小:",filesize; file_object.write('文件大小:'+filesize+'r'); #<div class="picthumb"><a href="//files.jb51.net/do/uploads/litimg/151210/1A9262GO2.jpg" target="_blank" bookimg = re.search('<divs+?class="picthumb"><a href="(?P<bookimg>.+?)" rel="external nofollow" target="_blank"', htmlcontent); if(bookimg): bookimg = bookimg.group("bookimg"); print "封面图片：",bookimg; file_object.write('封面图片:'+bookimg+'r'); #<li><a href="http://xz6.jb51.net:81/201512/books/JavaWeb100(jb51.net).rar" target="_blank">酷云中国电信下载</a></li> downurl1 = re.search('<li><a href="(?P<downurl1>.+?)" rel="external nofollow" target="_blank">酷云中国电信下载</a></li>', htmlcontent); if(downurl1): downurl1 = downurl1.group("downurl1"); print "下载地址1:",downurl1;  file_object.write('下载地址1:'+downurl1+'r'); sys.stdout.write('rFetching ' + title + '...n') title = title.replace(' ', ''); title = title.replace('/', ''); saveFile = '/Users/superl/Desktop/pythonbook/'+title+'.rar'; if os.path.exists(saveFile): print "该文件已经下载了！"; else: urllib.urlretrieve(downurl1, saveFile, reporthook=report); sys.stdout.write("rDownload complete, saved as %s" % (saveFile) + 'nn') sys.stdout.flush() file_object.write('文件下载成功!r'); else: print "下载地址1不存在"; file_error.write(url+'r'); file_error.write(title+"下载地址1不存在!文件没有自动下载！r"); file_error.write('r'); #<li><a href="http://pan.baidu.com/s/1pKfVNwJ" rel="external nofollow" target="_blank">百度网盘下载2</a></li> downurl2 = re.search('</a></li><li><a href="(?P<downurl2>.+?)" rel="external nofollow" target="_blank">百度网盘下载2</a></li>', htmlcontent); if(downurl2): downurl2 = downurl2.group("downurl2"); print "下载地址2:",downurl2;  file_object.write('下载地址2:'+downurl2+'r'); else: #file_error.write(url+'r'); print "下载地址2不存在";  file_error.write(title+"下载地址2不存在r"); file_error.write('r'); file_object.write('r'); print "n";def getBooksUrl(url): htmlcontent = getHtml(url); #<ul class="cur-cat-list"><a href="/books/438381.html" rel="external nofollow" class="tit"</ul></div><!--end #content --> urls = re.findall('<a href="(?P<urls>.+?)" rel="external nofollow" class="tit"', htmlcontent); for url in urls: url = "//www.jb51.net"+url; print url+"n"; file_object.write(url+'r'); getBookInfo(url) #print "url->", urlif __name__=="__main__": file_object = open('/Users/superl/Desktop/python.txt','w+'); file_error = open('/Users/superl/Desktop/pythonerror.txt','w+'); pagenum = 3; for pagevalue in range(1,pagenum+1): listurl = "//www.jb51.net/ books/list476_%d.html"%pagevalue; print listurl; file_object.write(listurl+'r'); getBooksUrl(listurl); file_object.close(); file_error.close();