def test_create_url(self):
p = Page()
p.save()
u = URL(TEST_URL)
u.add_content(p)
self.assertTrue(p.content_ptr in u.get_content(),
"URL does not point to correct content.")
def acortar(request):
if request.method == "GET":
URLs_guardadas = URL.objects.all()
plantilla_principal = get_template("pagina_principal.html")
Context = ({'lista_urls': URLs_guardadas})
return HttpResponse(plantilla_principal.render(Context))
elif request.method == "POST":
url = request.POST.get("url")
if url == "":
mensaje = "Está vacío"
plantilla_error = get_template("pagina_error.html")
Context = ({'mensaje': mensaje})
return HttpResponseBadRequest(plantilla_error.render(Context))
elif not url.startswith("http://") and not url.startswith("https://"):
url = "http://" + url
try:
nueva_URL = URL.objects.get(direccion_URL=url)
except URL.DoesNotExist:
nueva_URL = URL(direccion_URL=url)
nueva_URL.save()
plantilla_seleccion = get_template("pagina_seleccion.html")
id = nueva_URL.id
Context = ({'id': id})
return HttpResponse(plantilla_seleccion.render(Context))
else:
mensaje = "Algo ha ido mal"
plantilla_error = get_template("pagina_error.html")
Context = ({'mensaje': mensaje})
return HttpResponse(plantilla_error.render(Context))
def test_lookup_by_url(self):
p = Page()
p.save()
u = URL(TEST_URL)
u.add_content(p)
found = URL.objects.get(url=TEST_URL)
self.assertTrue(p.content_ptr in found.get_content(),
"Unable to find correct content by URL.")
def generate_hash():
if 'url' not in request.json or type(request.json['url']) != str:
return {
'status': 400,
'message': 'url either not found in body or invalid'
}, 400
long_url = request.json['url']
base_url = request.base_url
base_url = base_url.replace('/generate', '')
protocol = long_url.split('://')[0]
if protocol != 'http' and protocol != 'https':
return {
'status':
400,
'message':
'Invalid url in request body. URL must start with http or https'
}, 400
url_hash = URL.save_hash(long_url)
return {
'status': 200,
'message': 'URL generated successfully',
'url': f'{base_url}/{url_hash}'
}, 200
def insert_url(url:str, code:str) -> int:
"""Inserts a new URL"""
q = URL.insert(url=url, code=code)
url_id = q.execute()
Stats.insert(url=url_id, usage_count=0).execute()
return url_id
def parse_urls(session): # get name of file to read urlfile = os.path.join(os.path.expanduser(cfg.CURRENT_DIR), cfg.URLLOG) # read the file, write lines to database, and save lines that were not # written to the database # TODO may need to check if file is already open using a file lock if os.path.isfile(urlfile): f = open(urlfile, 'r+') lines_to_save = [] for line in f: try: text = ast.literal_eval(line.rstrip()) url = URL(unicode(text['time']), unicode(text['browser']), unicode(text['title']), unicode(text['url']), unicode(text['event'])) session.add(url) except: print "Could not save " + str(line) + " to the database. Saving for the next round of parsing." lines_to_save.append(line) # write lines that did not make it into the database to the start of the # file and delete the rest of the file f.seek(0) for line in lines_to_save: f.write(line) f.truncate() f.close()
def add(request):
if request.method == 'POST':
form = AddUserLinkForm(request.POST)
if form.is_valid():
if not form.cleaned_data['link'].startswith('http://'):
form.cleaned_data['link'] = 'http://' + form.cleaned_data['link']
if form.is_valid():
cd = form.cleaned_data
url = URL()
url.name = cd['label']
url.other_profile = cd['link']
url.user = request.user.get_profile()
url.type = URL.PERFORMANCES
url.save()
request.user.get_profile().save()
return HttpResponseRedirect(
'/links/' + request.user.get_profile().name + '/'
)
else:
form = AddUserLinkForm()
return render_to_response(
'add_user_link.html',
{
'form': form,
'all_tags': Tag.objects.all()
},
RequestContext(request))
def acorta(request):
if request.method == 'GET':
template = get_template('plantilla.html')
context = ({})
return HttpResponse(template.render(context))
elif request.method == 'POST':
url_original = request.POST['original']
print str(url_original)
if not url_original.find("http://"):
#print "tiene http://"
pass
elif not url_original.find("https://"):
#print "Tiene el https, no hace falta ponerlo"
pass
else:
#print "No lo tiene, ponemos el http://"
url_original = "http://" + url_original
try:
pages = URL.objects.all()
page = URL.objects.get(original=url_original)
cortada = len(pages) + 1
#page = URL.objects.get(original=url_original)
template = get_template('realizada.html')
context = ({'original':page.original, 'cortada':page.cortada})
respuesta = template.render(context)
except URL.DoesNotExist:
pages = URL.objects.all()
corta = len(pages) + 1
url_new = URL(original=url_original, cortada=corta)
url_new.save()
template = get_template('acortada.html')
context = ({'original':url_original, 'cortada':corta})
respuesta = template.render(context)
return HttpResponse(respuesta)
def redirect_url(url_hash):
long_url = URL.get_url(url_hash)
if not long_url:
return {
'status': 400,
'message': 'URL does not exist. Please try another one.'
}, 400
return redirect(long_url), 302
def shorten_url(url: str):
if not (url.startswith('https://') or url.startswith('http://')):
url = 'http://' + url
parsed_url = urlparse(url)
domain = parsed_url.netloc
if not domain.startswith('www.'):
domain = 'www.' + domain
path = parsed_url.path
sha_signature = hashlib.sha256((domain + path).encode()).hexdigest()
existing_urls = URL.query.filter(URL.domain == domain,
URL.path == path).all()
if existing_urls:
return 'localhost:5000/shorten/redirect/' + existing_urls[0].hash
obj = URL(domain=domain, path=path, hash=sha_signature, original_url=url)
db.session.add(obj)
db.session.commit()
return 'localhost:5000/shorten/redirect/' + obj.hash
def post(self):
url = urlfetch.fetch(self.request.get('content'))
doc = lxml.html.fromstring(url.content)
for sku in doc.cssselect('span'):
if sku.get('id') == 'displaySkuCode':
item_id = sku.text
registry_item = Item.get_by_id(item_id)
if registry_item is None:
registry_item = Item(id=item_id,
parent=ndb.Key("Website",
self.request.get('website')))
for tag in doc.cssselect('title'):
registry_item.title = tag.text.encode('utf-8')
for img in doc.cssselect('link'):
if img.get('rel') == 'image_src':
registry_item.img = img.get('href')
for price in doc.cssselect('div'):
if price.get('class') == 'sale-price':
for savings in price.cssselect('strong'):
registry_item.sale = savings.text.encode('utf-8')
if price.get('class') == 'reg-price':
registry_item.price = price.text.encode('utf-8').replace(
"Reg.", "")
registry_item.category = self.request.get('category')
registry_item.for_who = self.request.get('for_who')
registry_item.put()
link = URL.get_by_id(item_id)
if link is None:
link = URL(id=item_id,
parent=ndb.Key("Website", self.request.get('website')))
link.url = self.request.get('content')
link.last_scrape = datetime.datetime.now()
link.put()
self.redirect('/listings')
def post(self):
url = urlfetch.fetch(self.request.get('content'))
doc = lxml.html.fromstring(url.content)
for sku in doc.cssselect('span'):
if sku.get('id') == 'displaySkuCode':
item_id = sku.text
registry_item = Item.get_by_id(item_id)
if registry_item is None:
registry_item = Item(id=item_id, parent=ndb.Key("Website", self.request.get('website')))
for tag in doc.cssselect('title'):
registry_item.title = tag.text.encode('utf-8')
for img in doc.cssselect('link'):
if img.get('rel') == 'image_src':
registry_item.img = img.get('href')
for price in doc.cssselect('div'):
if price.get('class') == 'sale-price':
for savings in price.cssselect('strong'):
registry_item.sale = savings.text.encode('utf-8')
if price.get('class') == 'reg-price':
registry_item.price = price.text.encode('utf-8').replace("Reg.", "")
registry_item.category = self.request.get('category')
registry_item.for_who = self.request.get('for_who')
registry_item.put()
link = URL.get_by_id(item_id)
if link is None:
link = URL(id=item_id, parent=ndb.Key("Website", self.request.get('website')))
link.url = self.request.get('content')
link.last_scrape = datetime.datetime.now()
link.put()
self.redirect('/listings')
session.commit()
#
# if it's not a retweet
#
if not parentTweet:
links = re.findall(r"http:\/\/t.co\/[a-zA-Z0-9\-\.]+", text)
if links:
#
# let's remove the duplicates
#
links = list(set(links))
for link in links:
#
# if it's a real link
#
if is_ascii(link):
fetchedURL = session.query(URL).filter(
URL.shortAddress == link).first()
if not fetchedURL:
l = URL(link, u.ID)
session.add(l)
fetchedURL = l
fetchedURL.tweets.append(u)
session.commit()
count += 1
if count % 1000 == 0:
print "processed " + str(count) + " tweets"
def parse_geometries(session, activity_tracker):
# get names of file to read and the last arrangement
geofile = os.path.join(os.path.expanduser(cfg.CURRENT_DIR), cfg.GEOLOG)
q = session.query(Arrangement).order_by(Arrangement.id.desc()).first()
last_arr = ast.literal_eval(q.arr) if q else {}
# clean up dictionary for equal comparison
for a, va in last_arr.iteritems():
del va['pid']
for w, vw in va['windows'].iteritems():
del vw['wid']
del vw['gid']
# check if db file
if os.path.isfile(geofile):
f = open(geofile, 'r+')
lines_to_save = []
# get existing apps from the database
apps = session.query(App).all()
app_names = [a.name for a in apps]
# get existing windows from the database
windows = session.query(Window).all()
window_names = [w.title for w in windows]
# get existing geometries from the database
geometries = session.query(Geometry).all()
geometry_dicts = [[g.x, g.y, g.w, g.h] for g in geometries]
# get existing urls from the database
db_urls = session.query(URL).all()
urls = [d.url for d in db_urls]
for line in f:
try:
# get data
text = ast.literal_eval(line.rstrip())
t = text['time']
arrangement = text['geometry']
# if this is a duplicate of the last arrangement, don't record it
if arrangement == last_arr:
continue
# check for new windows opened or activated
for app, value in arrangement.iteritems():
app_name = value['name']
active = value['active']
windows = value['windows']
# add new apps to the database, but should not need to to this
if app_name not in app_names:
# add app to the database
app_to_add = App(t, app_name)
session.add(app_to_add)
activity_tracker.storage.sqlcommit()
# update our local app list
apps = session.query(App).all()
app_names = [a.name for a in apps]
# add the app's pid to the arrangement dictionary
pid = app_names.index(app_name) + 1 # array starts at 0, database ids a 1
value['pid'] = pid # removing for now, may want to add back later, but will need new arrangement comparison method
for window, val in windows.iteritems():
# get window information
title = val['name']
w_active = val['active']
bounds = val['bounds']
x = int(bounds['x'])
y = int(bounds['y'])
width = int(bounds['width'])
height = int(bounds['height'])
# add new windows to the database, but should not need to do this
if title not in window_names:
# add app to the database
app_to_add = Window(t, pid, title)
session.add(app_to_add)
activity_tracker.storage.sqlcommit()
# update our local window list
windows = session.query(Window).all()
window_names = [w.title for w in windows]
# add the window's wid to the window dictionary
wid = window_names.index(title) + 1 # array starts at 0, database ids a 1
val['wid'] = wid # removing for now, may want to add back later, but will need new arrangement comparison method
# add new geometries to the database
gd = [x, y, width, height]
if gd not in geometry_dicts:
ge = Geometry(t, x, y, width, height)
session.add(ge)
activity_tracker.storage.sqlcommit()
# update our local geomery list
geometries = session.query(Geometry).all()
geometry_dicts = [[g.x, g.y, g.w, g.h] for g in geometries]
# add the geometry's gid to the window dictionary
gid = geometry_dicts.index(gd) + 1 # array starts at 0, database ids a 1
val['gid'] = gid # removing for now, may want to add back later, but will need new arrangement comparison method
# add new urls to the database
if 'tabs' in val.keys():
tabs = val['tabs']
for tab, tval in tabs.iteritems():
t_active = tval['active']
t_url = tval['url']
if tval['url'] not in urls:
u = URL(t, tval['title'], tval['url'], tval['host'])
session.add(u)
activity_tracker.storage.sqlcommit()
# update our local urls list
db_urls = session.query(URL).all()
urls = [d.url for d in db_urls]
# add the url's uid to the window dictionary
uid = urls.index(tval['url']) + 1 # array starts at 0, database ids a 1
tval['uid'] = uid
#TODO create url open, close, active, inactive events
if not app in last_arr:
te = URLEvent(t, uid, pid, wid, "Open")
session.add(te)
if t_active:
te = URLEvent(t, uid, pid, wid, "Open")
session.add(te)
elif not window in last_arr[app]['windows']:
te = URLEvent(t, uid, pid, wid, "Open")
session.add(te)
if t_active:
te = URLEvent(t, uid, pid, wid, "Active")
session.add(te)
elif not tab in last_arr[app]['windows'][window]['tabs']:
te = URLEvent(t, uid, pid, wid, "Open")
session.add(te)
if t_active:
te = URLEvent(t, uid, pid, wid, "Active")
session.add(te)
elif t_active and (not last_arr[app]['windows'][window]['tabs'][tab]['active'] or t_url != last_arr[app]['windows'][window]['tabs'][tab]['url']):
te = URLEvent(t, uid, pid, wid, "Active")
session.add(te)
# create open and active events if...
# this app was not even open the last time around
if not app in last_arr:
we = WindowEvent(t, wid, "Open")
session.add(we)
if w_active:
we = WindowEvent(t, wid, "Active")
session.add(we)
else:
# or if the window was not present last time
if not window in last_arr[app]['windows']:
we = WindowEvent(t, wid, "Open")
session.add(we)
if w_active:
we = WindowEvent(t, wid, "Active")
session.add(we)
else:
# or the window was present but not active last time, or had a different name
if w_active and (not last_arr[app]['windows'][window]['active'] or title != last_arr[app]['windows'][window]['name']):
we = WindowEvent(t, wid, "Active")
session.add(we)
# add new arrangement to the database
arr_to_add = Arrangement(t, str(arrangement))
session.add(arr_to_add)
# look now at the last arrangement to see what has closed or gone inactive
for app, value in last_arr.iteritems():
app_name = value['name']
active = value['active']
windows = value['windows']
if app_name not in app_names:
# add app to the database
app_to_add = App(t, app_name)
session.add(app_to_add)
#TODO catch if our commit fails
activity_tracker.storage.sqlcommit()
# update our local app list
apps = session.query(App).all()
app_names = [a.name for a in apps]
pid = app_names.index(app_name) + 1 # array starts at 0, database ids a 1
for window, val in windows.iteritems():
# get window information
title = val['name']
w_active = val['active']
bounds = val['bounds']
x = bounds['x']
y = bounds['y']
w = bounds['width']
h = bounds['height']
if title not in window_names:
# add app to the database
app_to_add = Window(t, pid, title)
session.add(app_to_add)
#TODO catch if our commit fails
activity_tracker.storage.sqlcommit()
# update our local app list
windows = session.query(Window).all()
window_names = [w.title for w in windows]
wid = window_names.index(title) + 1 # array starts at 0, database ids a 1
if 'tabs' in val.keys():
tabs = val['tabs']
for tab, tval in tabs.iteritems():
uid = urls.index(tval['url']) + 1
t_active = tval['active']
t_url = tval['url']
if not app in arrangement:
te = URLEvent(t, uid, pid, wid, "Close")
session.add(te)
if t_active:
te = URLEvent(t, uid, pid, wid, "Inactive")
session.add(te)
elif not window in arrangement[app]['windows']:
te = URLEvent(t, uid, pid, wid, "Close")
session.add(te)
if t_active:
te = URLEvent(t, uid, pid, wid, "Inactive")
session.add(te)
elif not tab in arrangement[app]['windows'][window]['tabs']:
te = URLEvent(t, uid, pid, wid, "Close")
session.add(te)
if t_active:
te = URLEvent(t, uid, pid, wid, "Inactive")
session.add(te)
elif t_active and (not arrangement[app]['windows'][window]['tabs'][tab]['active'] or t_url != arrangement[app]['windows'][window]['tabs'][tab]['url']):
te = URLEvent(t, uid, pid, wid, "Inactive")
session.add(te)
# create close and inactive events if...
# this app is not longer present
if not app in arrangement:
we = WindowEvent(t, wid, "Close")# create open event
session.add(we)
if w_active:
we = WindowEvent(t, wid, "Inactive")# create open event
session.add(we)
else:
# or if the window is not longer present
if not window in arrangement[app]['windows']:
we = WindowEvent(t, wid, "Close")# create open event
session.add(we)
if w_active:
we = WindowEvent(t, wid, "Inactive")# create open event
session.add(we)
else:
# or the window is present but no longer active, or has a different name
if w_active and (not arrangement[app]['windows'][window]['active'] or title != arrangement[app]['windows'][window]['name']):
we = WindowEvent(t, wid, "Inactive")# create open event
session.add(we)
last_arr = copy.deepcopy(arrangement)
except:
print "Could not save " + str(line) + " to the database. Saving for the next round of parsing."
lines_to_save.append(line)
# write lines that did not make it into the database to the start of the
# file and delete the rest of the file
f.seek(0)
for line in lines_to_save:
f.write(line)
f.truncate()
f.close()
def url(request, url):
if request.method == 'GET':
if url == '':
respuesta = '<form method="POST" action="">' \
+ 'URL: <input type="text" name="url"><br>' \
+ '<input type="submit" value="Enviar"><br>' \
+ '</form>'
paginas = URL.objects.all()
for pagina in paginas:
respuesta += '<li><a href="/' + str(pagina.URLcorta) + '">' + str(pagina.URLlarga) + '</a>'
respuesta += '<li><a href="/' + str(pagina.URLcorta) + '">' + str(pagina.URLcorta) + '</a>'
else:
try:
pagina = URL.objects.get(URLcorta=url)
respuesta = '<html><head><meta http-equiv="Refresh" content="5;url='+ pagina.URLlarga +'"></head>' \
+ "<body><h1> Espere, va a ser redirigido en 5 segundos... " \
+ "</h1></body></html>"
except URL.DoesNotExist:
try:
url = 'http://localhost:1234/' + str(url)
pagina = URL.objects.get(URLcorta=url)
respuesta = '<html><head><meta http-equiv="Refresh" content="5;url='+ pagina.URLlarga +'"></head>' \
+ "<body><h1> Espere, va a ser redirigido en 5 segundos... " \
+ "</h1></body></html>"
except URL.DoesNotExist:
respuesta = '<h1><font color ="red">Lo sentimos esta pagina no ha sido almacenada.</font></h1>'
return HttpResponse(respuesta)
elif request.method == 'POST' or request.method == 'PUT':
urlparaacortar = request.body.split("=")[1]
urlparaacortar = urllib.unquote(urlparaacortar).decode('utf8')
http = urlparaacortar.split("://")[0]
if (http != 'http') and (http != 'https'):
urlparaacortar = 'https://' + str(urlparaacortar)
try:
urlcorta = URL.objects.get(URLlarga=urlparaacortar)
respuesta = '<h1>Esta URL ya ha sido acortada </h1></br>'\
+'<html><body><a href="'+ urlparaacortar +'">' + urlparaacortar + ' </a></br></body></html>'\
+ '<html><body><a href="'+ urlcorta.URLcorta +'">'+ urlcorta.URLcorta + ' </a></br></body></html>'
except URL.DoesNotExist:
paginas = URL.objects.all()
contador = 0
for pagina in paginas:
contador = contador + 1
urlnuevacorta = 'http://localhost:1234/' + str(contador)
p = URL(URLcorta=urlnuevacorta, URLlarga=urlparaacortar)
p.save()
pagina = URL.objects.get(URLcorta=urlnuevacorta)
respuesta = "<h1>Se ha acortado la URL de forma correcta</br></h1>" \
+'<a href="'+ str(pagina.URLlarga) +'">' + str(pagina.URLlarga) + ' </a></br>'\
+ '<a href="'+ str(pagina.URLcorta) +'">'+ str(pagina.URLcorta) + ' </a></br>'
return HttpResponse(respuesta)
else:
respuesta= 'Ha ocurrido un error'
return HttpResponse(respuesta)
