Last active
February 27, 2016 10:20
-
-
Save yne/599420215e8df4bb8054 to your computer and use it in GitHub Desktop.
Website as filesystem testing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import os,re,sys,json,errno,urllib2,urllib,threading | |
from fuse import FUSE, FuseOSError, Operations | |
class MyWebsite(Operations): | |
def __init__(self, root): | |
self.root = root | |
self.files = {} | |
self.cache = {} | |
self.ua = {'User-Agent':'Mozilla/5.0' } | |
self.routes = [ | |
{'path':'^/$' ,'url':'community' ,'find':'ref="/c/[-a-z_]+?/','map':lambda a:a[8:-1]}, | |
{'path':'^/([-a-z_]+)_videos$' ,'url':'c/%s_videos/videos' ,'find':'sample-video=".*?"','map':lambda a:urllib.quote('http:'+a[14:-1], safe='')}, | |
{'path':'^/([-a-z_]+)$' ,'url':'c/%s/albums' ,'find':'/albums/.+?/view/' ,'map':lambda a:a[8:-6]}, | |
{'path':'^/.*?/([-a-z_0-9]+_\d+)$' ,'url':'c/-/pictures/album/%s' ,'find':'src="//[ic].+?"' ,'map':lambda a:urllib.quote('http:'+a[ 5:-1], safe='')}, | |
{'path':'^/([-a-z_]+)/(\+[-+a-z_0-9]+)$' ,'url':'c/%s/albums/tagged/%s' ,'find':'/albums/.+?/view/' ,'map':lambda a:a[8:-6]}, | |
{'path':'^/([-a-z_]+)/([-a-z_0-9]+)$' ,'url':'c/%s/pictures/frontpage/0/text/%s' ,'find':'src="//[ic].+?"' ,'map':lambda a:urllib.quote('http:'+a[ 5:-1], safe='')}, | |
] | |
def fetch_thread(self,path,target,fh,attrs): | |
url = urllib.unquote(os.path.basename(path)) | |
target[fh] = "" | |
try: | |
target[fh] = urllib2.urlopen(urllib2.Request(url,None,self.ua)).read() | |
attrs[path]['st_size']=len(target[fh]) | |
try: | |
url = url.replace('.100x100','.315x0') | |
target[fh] = urllib2.urlopen(urllib2.Request(url,None,self.ua)).read() | |
attrs[path]['st_size']=len(target[fh]) | |
except urllib2.HTTPError,e: | |
pass | |
url = url.replace('.315x0','') | |
target[fh] = urllib2.urlopen(urllib2.Request(url,None,self.ua)).read() | |
attrs[path]['st_size']=len(target[fh]) | |
except urllib2.HTTPError,e: | |
print "ERROR>>>",e,url,len(target[fh]) | |
if len(target[fh])==0: | |
del target[fh] | |
def fetch(self, path, page=1): | |
for r in self.routes: | |
g = re.match(r['path'],path) | |
if not g:continue | |
url = 'http://'+self.root+'/'+r['url']%g.groups()+'/page/%d/'%page | |
try: | |
html = urllib2.urlopen(urllib2.Request(url,None,self.ua)).read() | |
link = map(r['map'],re.findall(r['find'],html)) | |
return sorted(set(link), key=lambda x: link.index(x)) | |
except urllib2.HTTPError,e: | |
print e,url | |
break | |
#STRUCTURE OPERATION | |
def getattr(self, path, fh=None): | |
#attrs = ('st_atime', 'st_ctime', 'st_gid', 'st_mode', 'st_mtime', 'st_nlink', 'st_size', 'st_uid') | |
if not self.cache.has_key(path): | |
return {'st_mode': 040666, 'st_size': 0, 'f':[], 'page':0} | |
return self.cache[path] | |
def readdir(self, path, fh): | |
#only handle visible files | |
if '.' not in path[:2]: | |
#send the 2 mandatory nodes | |
for dots in ['.', '..']:yield dots; | |
#the dir is on RAM : send it all | |
if path in self.cache and 'complete' in self.cache[path]: | |
for d in self.cache[path]['f']:yield d.strip("/") | |
else:#the dir doesn't exist or is unfinished | |
if path not in self.cache: | |
self.cache[path]={'st_mode': 040444, 'st_size': 0,'f':[],'page':0} | |
#the dir now exist, fill+yield it while we can and mark it as complete | |
for i in xrange(1,20): | |
self.cache[path]['page'] += 1 | |
results = self.fetch(path,self.cache[path]['page']) or [] | |
#print "FETCH>>>",path,self.cache[path]['page'],len(results) | |
if not results:break | |
for r in results: | |
self.cache[path]['f'].append(r) | |
self.cache[os.path.join(path,r)] = {'st_mode': 0100666 if r[:4]=='http' else 040666, 'st_size': 4, 'f':[], 'page':0} | |
yield r | |
self.cache[path]['complete']=True | |
#FILE OPERATION | |
def open(self, path, flags): | |
fh=hash(path)&0x0FFFFFFFL | |
if not fh in self.files: | |
threading.Thread(target = self.fetch_thread, args = (path,self.files,fh,self.cache)).start() | |
return fh | |
def read(self, path, length, offset, fh): | |
f = self.files.get(fh,'') | |
return f[offset:offset+length] | |
def release(self, path, fh): | |
#self.cache[path]['thread'].join(1) | |
#self.files[fh]="" | |
return 0 | |
if __name__ == '__main__': | |
FUSE(MyWebsite(sys.argv[1]), sys.argv[2], nothreads=True, foreground=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment