def get_json(topic):
r = requests.get('http://itunes.apple.com/search?term=' + topic +
'&entity=software&limit=300')
j = simplejson.loads(r.content)
for i in j['results']:
if not Apps.objects.filter(name=get_name(i)):
if (i['primaryGenreName'] in ['Education', 'Reference']) or (
('Education' in i['genres']) and
(i['primaryGenreName'] in acceptable_topics)):
try:
m1 = Apps(name=get_name(i),
description=get_description(i),
creator=get_creator(i),
subject=i['primaryGenreName'],
price=get_price(i),
rating=get_rating(i),
artwork=get_artwork(i),
link=get_link(i))
# date_added=datetime.datetime.now()) <-- check if needed
m1.save()
print get_name(i) + " was added to the database! ", topic
except:
print get_name(i), get_link(i)
raise
else:
print get_name(i) + " is not an Education app! " + str(
i['genres'])
def add_to_db(d): for entry in d: if not Apps.objects.filter(name=entry): m1 = Apps(name=entry, platform=d[entry]['platform'], creator=d[entry]['creator'], subject=d[entry]['subject'], price=d[entry]['price'], rating=d[entry]['rating'], artwork=d[entry]['artwork'], link=d[entry]['link']) m1.save() else: print "The app '%s' is already in the database!" % entry
def add_update(link, val):
# future: find downloads, age, comment
soup = get_soup(link)
name = get_name(soup)
creator = get_creator(soup)
platform = get_platform(soup)
subject = get_subject(soup)
if subject == 'NotEducation': # change to "creator == 'NotEducation', set in classifier"
print "The app '%s' is not Education-related and was not added to the database!" % name
else:
price = get_price(soup)
rating = get_rating(soup)
artwork = get_artwork(soup)
if val == 0:
m1 = Apps(name=name,
platform=platform,
creator=creator,
subject=subject,
price=price,
rating=rating,
artwork=artwork,
link=link,
date_added=datetime.datetime.now())
m1.save()
print "The app '%s' was successfully added to the database!" % name
elif val == 1:
m1 = Apps.objects.get(link=link)
m1.update(name=name,
platform=platform,
creator=creator,
subject=subject,
price=price,
rating=rating,
artwork=artwork,
link=link)
print "The app '%s' was successfully updated!" % name
else:
print "What the hell are you doing with your code!?"
def page_to_db(link):
# downloads, age, comment
foobar = requests.get(link).text
soup = BeautifulSoup(foobar)
# get_name
try:
a = re.compile('<title>.+</title>').findall(str(soup))
title = a[0]
begin, end = title.index('>') + 1, title.index('<', 1)
full_name = title[begin:end]
if 'App Store - ' in full_name:
name = full_name[full_name.index('Store - ') + 8:]
elif ' for iP' in full_name:
name = full_name[:full_name.index(' for iP')]
else:
name = full_name
except (AttributeError, ValueError, TypeError):
name = link
print "Error retrieving name from %s." % link
# get_creator
try:
a = soup.find('div', {'class': 'lockup product application'})
b = str(
a.find('li', {
'class': 'copyright'
}).previous_sibling.get_text())
creator = b[8:]
except (AttributeError, ValueError, TypeError):
creator = ''
print "Error retrieving creator for %s." % name
# get_platform
try:
platform = list(soup.find_all('a', {'metrics-loc': 'Pill_'})) # list
for key, value in enumerate(platform):
platform[key] = re.compile('>[^<]*<').findall(
str(value))[0].lstrip('>').rstrip('<')
platform = '/'.join(platform[:])
except (AttributeError, ValueError, TypeError):
platform = ''
print "Error retrieving platform for %s." % name
# get_subject
try:
a = soup.find('div', {'class': 'lockup product application'})
subject = str(
a.find('span', {
'class': 'label'
}).next_sibling.get_text())
except (AttributeError, ValueError, TypeError):
subject = ''
print "Error retrieving subject for %s." % name
# get_price
try:
price_text = soup.find('div', {'class': 'price'}).get_text()
try:
price = float(price_text[1:]) # get rid of $ in front
except ValueError:
if price_text == ("Free" or "free"):
price = float(0)
else:
price = None
print "Error retrieving float-type price for %s." % name
except (AttributeError, TypeError):
price = None
print "Error retrieving price for %s." % name
# get_rating
try:
rating_text = soup.find('div', {'class': 'rating'}).get('aria-label')
rating_num = re.compile('[0-5]\.?[0-9]*').findall(rating_text)
rating = float(rating_num[0])
except AttributeError:
try:
rating_text = soup.find('div', {
'class': 'app-rating'
}).a.get_text()
rating_num = re.compile('[0-5]\.?[0-9]*').findall(rating_text)
rating = float(rating_num[0])
except (AttributeError, IndexError, TypeError, ValueError):
rating = None
except (IndexError, ValueError, TypeError):
rating = None
print "Error retrieving rating for %s." % name
# get_artwork
try:
artwork = str(soup.find('img', {'class': 'artwork'}).get('src'))
except (AttributeError, ValueError, TypeError):
artwork = ''
print "Error retrieving artwork for %s." % name
m1 = Apps(name=name,
platform=platform,
creator=creator,
subject=subject,
price=price,
rating=rating,
artwork=artwork,
link=link,
crawl_binary=0,
date_added=datetime.datetime.now())
m1.save()
print "The app '%s' was successfully added to the database!" % name