清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>
import urllib import re import os import sys lst="myz.lst" bak_lst=lst+".bak" urls=[] def check(): if os.path.exists(lst): with open(lst,'r') as f: cnt=f.read() if cnt: urls=cnt.split("\n") with open(bak_lst,'w') as ff: ff.write(cnt) rlt=urllib.urlopen("http://www.xlpu.cc/html/42829.html?encode=1").read() al=re.findall(r'href="(thun.*?)"',rlt,re.S) rlt=set(al)-set(urls) if not rlt: print "No Change" else: with open(lst,'w') as f: f.write("\n".join(rlt)) len_urls=len(rlt) print "%d movies add"%len_urls for ix,url in enumerate(rlt): print "[%d/%d]"%(ix+1,len_urls),url def reset(): if os.path.exists(bak_lst): os.remove(lst) os.rename(bak_lst,lst) if __name__=="__main__": if "--reset" in sys.argv: reset() else: check()