python脚本爬取字体文件的实现方法

#coding:utf-8import urllib2,cookielib,sys,re,os,zipfileimport numpy as np#网站登陆cj=cookielib.CookieJar()opener=urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))opener.addheaders=[('User-agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36))')]urllib2.install_opener(opener)#搜索可下载连接def search(path): request=urllib2.Request(path) response=urllib2.urlopen(request) html=response.read() html=html.replace('/n',' ')#将所有的回车去掉，因为正则表达式是单行匹配。。。。。。 urls=re.findall(r'<a href="(.*?)" rel="external nofollow" >(.*?)</a>',html) for i in urls:  url,inner=i  if not re.findall(r'Download ',inner)==[] and re.findall(r'offsite',inner)==[] and url not in items:   items.append(url)items=[]#保存下载地址for i in xrange(15): host='http://www.fontsquirrel.com/fonts/list/find_fonts/'+str(i*50)+'?filter%5Bdownload%5D=local' search(host)if not os.path.exists('ttf'): os.mkdir('ttf')os.chdir('ttf')def unzip(rawfile,outputdir): if zipfile.is_zipfile(rawfile):  print 'yes'  fz=zipfile.ZipFile(rawfile,'r')  for files in fz.namelist():   print(files) #打印zip归档中目录   fz.extract(files,outputdir)#解压缩文件 else:  print 'no'for i in items:  print i request=urllib2.Request('http://www.fontsquirrel.com'+i) response=urllib2.urlopen(request) html=response.read() name=i.split('/')[-1]+'.zip' f=open(name,'w') f.write(html) f.close()#文件记得关闭，否则下面unzip会出错 unzip(name,'./') os.remove(name)os.listdir(os.getcwd())os.chdir('../')files=os.listdir('ttf/')for i in files:#删除无用文件 if not (i.split('.')[-1]=='ttf' or i.split('.')[-1]=='otf'):  if os.path.isdir(i):   os.removedirs('ttf/'+i)  else:   os.remove('ttf/'+i)print len(os.listdir('ttf/'))

#coding:utf-8import urllib2,cookielib,sys,re,os,zipfileimport shutilimport numpy as npcj=cookielib.CookieJar()opener=urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))opener.addheaders=[('User-agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36))')]urllib2.install_opener(opener)items=[]def search(path): request=urllib2.Request(path) response=urllib2.urlopen(request) html=response.read() html=html.replace('/n',' ') urls=re.findall(r'href=/"(http://dl.dafont.com/dl//?f=.*?)/" >',html) items.extend(urls)for i in xrange(117): host='http://www.dafont.com/new.php?page='+str(i+1) search(host) print 'Page'+str(i+1)+'done' items=list(set(items)) print len(items)if not os.path.exists('ttf2'): os.mkdir('ttf2')os.chdir('ttf2')def unzip(rawfile,outputdir): if zipfile.is_zipfile(rawfile):  print 'yes'  fz=zipfile.ZipFile(rawfile,'r')  for files in fz.namelist():   print(files) #打印zip归档中目录   fz.extract(files,outputdir) else:  print 'no'for i in items:  print i request=urllib2.Request(i) response=urllib2.urlopen(request) html=response.read() name=i.split('=')[-1]+'.zip' f=open(name,'w') f.write(html) f.close() unzip(name,'./') os.remove(name)print os.listdir(os.getcwd())for root ,dire,fis in os.walk('./'):#递归遍历文件夹 for i in fis:  if not (i.split('.')[-1]=='ttf' or i.split('.')[-1]=='otf'):   os.remove(root+i)   print ifor i in os.listdir('./'): if os.path.isdir(i):  os.rmdir(i)os.chdir('../')