def url(self):
"""
The URL representing the search request.
"""
url = 'http://www.gaspedaal.nl/{0}/{1}/?srt=df&p={2}'.format(
q(self.brand), q(self.model), self.page)
if len(self.parameters) > 0:
pairs = ['{0}={1}'.format(q(k), q(str(v)))
for k, v in self.parameters.items()]
url += '&' + '&'.join(pairs)
return url
def _test(self, arg):
"""tests a command on a different bunny1 host. usage: _test [fully-qualified-bunny1-url] [command]"""
(bunny1_url, arg) = arg.split(None, 1)
if not bunny1_url.endswith("?"):
bunny1_url += "?"
save("bunny1testurl", bunny1_url)
raise HTTPRedirect(bunny1_url + q(arg))
def cached_requests(url):
### CACHED FILE RELATIVE PATH ###
cached_filename = os.path.join(CACHE_DIR, q(url))
contents = ""
### IF THE RESULT IS PRESENT IN CACHED DIRECTORY ###
if os.path.exists(cached_filename):
with open(cached_filename, "r") as read_file:
contents = read_file.read()
else:
print(f"Requesting URL: {url}")
if ENABLE_REQUESTS is False:
raise RuntimeError("Declining request as ENABLE_REQUESTS is False")
# Rate limit our requests
if RATE_LIMIT_DURATION:
print(
f"Pausing for {RATE_LIMIT_DURATION} seconds as rate limiting")
time.sleep(RATE_LIMIT_DURATION)
# Make our request and verify it was a 200
req = requests.get(url)
req.raise_for_status()
### SAVED THE RESULT IN THE CACHE ###
contents = req.text
if not os.path.exists(CACHE_DIR):
os.mkdir(CACHE_DIR)
with open(cached_filename, "w") as write_file:
write_file.write(contents)
return contents
def Search(self):
cards = []
listingsURL = []
pagenum = '1'
try:
site = requests.get('https://www.olx.bg/ads/q-' + q(self.keyword))
pagenum = bs(site.content, "lxml").find("a", {"data-cy": "page-link-last"}).find('span').find(text=True)
except:
pass
counter = []
count = 0
while count < int(pagenum):
count = count + 1
counter.append(count)
for number in counter:
search = requests.get('https://www.olx.bg/ads/q-'+q(self.keyword)+'/?page='+str(number))
home = bs(search.content, "lxml")
listings = home.find_all("a", {"data-cy": "listing-ad-title"})
for listing in listings:
if listing['href'][-8:] != 'promoted':
listingsURL.append(listing['href'])
print(len(listingsURL))
for listing in listingsURL:
url=requests.get(listing)
home = bs(url.content, "lxml")
title=price=address=data=name=link=''
try:
title = home.find('h1').find(text=True).strip()
address = home.find('address').find("p").find(text=True).strip()
data = home.find('div',{"id":"textContent"}).find(text=True).strip()
name = home.find('div',{"class", "offer-user__actions"}).find('h4').find('a').find(text=True).strip()
link = listing
price = home.find('strong', {"class": "pricelabel__value"}).find(text=True).strip()
except:
pass
card = {
"Title":title,
"Price":price,
"Address":address,
"Description":data,
"Name" :name,
"Link" :link
}
cards.append(card)
return cards
def model_filename(clf_class, tr_set, *features, **clf_params):
'''converts the given argument to a model filename, with extension
.sklmodel'''
pars = odict()
pars['clf'] = [str(clf_class.__name__)]
pars['tr_set'] = [
str(_) for _ in
(tr_set if isinstance(tr_set, (list, tuple)) else [tr_set])
]
pars['feats'] = [str(_) for _ in sorted(features)]
for key in sorted(clf_params):
val = clf_params[key]
pars[q(key, safe=_safe)] = [
str(_) for _ in
(val if isinstance(val, (list, tuple)) else [val])
]
return '&'.join("%s=%s" % (k, ','.join(q(_, safe=_safe) for _ in v))
for k, v in pars.items()) + '.sklmodel'
def fallback(self, raw):
raise HTTPRedirect(self.fallback_url + q(raw))
def _t(self, arg):
"""tests a command on the most recently used bunny1 host. usage: _t [command]"""
bunny1_url = load("bunny1testurl")
raise HTTPRedirect(bunny1_url + q(arg))
def g(self, arg):
"""does a google search. we could fallback to yubnub, but why do an unnecessary roundtrip for something as common as a google search?"""
return GOOGLE_SEARCH_URL + q(arg)
