def __init__(self,
screen_size='',
max_screen_resolution='',
chipset_brand='',
card_description='',
brand='',
item_weight='',
operating_system='',
computer_memory_type='',
batteries='',
date_first_available=''):
self.screen_size = screen_size
self.max_screen_resolution = max_screen_resolution
self.brand = chipset_brand
self.card_description = card_description
self.brand_name = brand
self.item_weight = item_weight
self.operating_system = operating_system
self.computer_memory_type = computer_memory_type
self.batteries = batteries
self.date = date_first_available
# Check if we didn't get empty values from the scraping.
# If valid is 0, I will retry the scraping.
if self.screen_size != '' or self.max_screen_resolution != '' or self.brand != '' \
or self.card_description != '' or self.brand_name != '' or self.item_weight != '' \
or self.operating_system != '' or self.computer_memory_type != '' or self.batteries != '':
self.valid = 1
else:
self.valid = 0
self.con = connect_to_db()
self.cur = self.con.cursor()
def get_reviews_content():
"""Select all the profiles of the users from the reviews table"""
con = connect_to_db()
cur = con.cursor()
cur.execute("SELECT Review_id, Content FROM reviews")
db_output = [item for item in cur.fetchall()]
return db_output
def profile():
"""Select all the profiles of the users from the reviews table"""
con = connect_to_db()
cur = con.cursor()
cur.execute("SELECT DISTINCT Profile_link FROM reviews")
db_output = [item for item in cur.fetchall()]
con.close()
return db_output
def add_sentiment_to_db(review_id, polarity, subjectivity, polarity_conf, subjectivity_conf):
con = connect_to_db()
cur = con.cursor()
cur.execute("""UPDATE reviews
SET Polarity=%s, Subjectivity=%s, Polarity_confidence=%s, Subjectivity_confidence=%s
WHERE Review_id =%s""",(polarity, subjectivity, polarity_conf, subjectivity_conf, review_id))
con.commit()
con.close()
def __init__(self, user_id, username, location, date, rank, profile, cont):
self.user_id = user_id
self.username = username
self.location = location
self.date = date
self.rank = rank
self.profile = profile
self.content = cont
self.con = connect_to_db()
self.cur = self.con.cursor()
def valid_features():
"""Check the validity of the features that were added to the table laptop_features,
and re-scrape and update the corresponding records in case it was not valid."""
con = connect_to_db()
cur = con.cursor()
cur.execute("SELECT Link, Laptop_id FROM laptop_features WHERE Valid=0")
db_output = [item for item in cur.fetchall()]
con.close()
for my_url in db_output:
feat = scraper_class.Parameters(config.AMAZON + my_url[0])
laptop = feat.get_param()
laptop.update_db(my_url[1])
def __init__(self, user_id, ranking='', review='', votes=''):
self.username = user_id
self.ranking = ranking
self.review = review
self.votes = votes
# Check if we didn't get empty values from the scraping.
# If valid is 0, I will retry the scraping.
if self.review == 0 and self.ranking == 0 and self.ranking == 0:
self.valid = 0
else:
self.valid = 1
self.con = connect_to_db()
self.cur = self.con.cursor()
def __init__(self, name, price, rating, reviews, link):
self.name = str(name.encode('utf-8', errors='ignore').decode('utf-8'))
self.price = price
self.rating = rating
self.reviews = reviews
self.link = link
# Check if we didn't get empty values from the scraping.
# If valid is 0, I will retry the scraping.
if self.price != 0 or self.rating != -1 or self.reviews != 0:
self.valid = 1
else:
self.valid = 0
self.con = connect_to_db()
self.cur = self.con.cursor()