|
|
@ -31,39 +31,35 @@ def wethenorth_description_parser(soup): |
|
|
left = "-1" # 16 Product_QuantityLeft |
|
|
left = "-1" # 16 Product_QuantityLeft |
|
|
shipFrom = "-1" # 17 Product_ShippedFrom |
|
|
shipFrom = "-1" # 17 Product_ShippedFrom |
|
|
shipTo = "-1" # 18 Product_ShippedTo |
|
|
shipTo = "-1" # 18 Product_ShippedTo |
|
|
|
|
|
image = "-1" # 19 Product_Image |
|
|
|
|
|
vendor_image = "-1" # 20 Vendor_Image |
|
|
|
|
|
|
|
|
# Finding Product Name |
|
|
# Finding Product Name |
|
|
listDes = soup.find('div', {'class': "listDes"}) |
|
|
listDes = soup.find('div', {'class': "listDes"}) |
|
|
name = listDes.find('h2').text |
|
|
name = listDes.find('h2').text |
|
|
name = name.replace('\n', ' ') |
|
|
|
|
|
name = name.replace(",", "") |
|
|
|
|
|
|
|
|
name = cleanString(name) |
|
|
name = name.strip() |
|
|
name = name.strip() |
|
|
|
|
|
|
|
|
# Finding Vendor |
|
|
# Finding Vendor |
|
|
vendor = listDes.find('b').text |
|
|
vendor = listDes.find('b').text |
|
|
vendor = vendor.replace(",", "") |
|
|
|
|
|
vendor = vendor.replace("...", "") |
|
|
|
|
|
vendor = vendor.replace("-", "") |
|
|
|
|
|
|
|
|
vendor = cleanString(vendor) |
|
|
vendor = vendor.strip() |
|
|
vendor = vendor.strip() |
|
|
|
|
|
|
|
|
# Finding Vendor Rating |
|
|
# Finding Vendor Rating |
|
|
rating = listDes.find('span',{'class':'levelSet'}) |
|
|
|
|
|
|
|
|
rating = listDes.find('span', {'class': 'levelSet'}) |
|
|
rating = rating.text |
|
|
rating = rating.text |
|
|
rating = rating.replace('\n', ' ') |
|
|
|
|
|
rating = rating.replace(",", "") |
|
|
|
|
|
rating = rating.strip() |
|
|
|
|
|
|
|
|
|
|
|
# Finding Successful Transactions |
|
|
|
|
|
success = listDes.find_all('p')[1] |
|
|
|
|
|
success = success.find('span').text |
|
|
|
|
|
success = success.split() |
|
|
|
|
|
success = success[0].strip() |
|
|
|
|
|
|
|
|
rating = cleanNumbers(rating) |
|
|
|
|
|
rating_vendor = rating.strip() |
|
|
|
|
|
|
|
|
# Finding Prices - all prices in We The North are in CAD, I left the CAD in the resulting String so that it would show CAD for all prices |
|
|
# Finding Prices - all prices in We The North are in CAD, I left the CAD in the resulting String so that it would show CAD for all prices |
|
|
padp = listDes.find('p',{'class':'padp'}) |
|
|
|
|
|
|
|
|
padp = listDes.find('p', {'class': 'padp'}) |
|
|
USD = padp.find('span').text |
|
|
USD = padp.find('span').text |
|
|
USD = USD.strip() |
|
|
USD = USD.strip() |
|
|
|
|
|
|
|
|
|
|
|
BTC = padp.find_next_sibling('p').text |
|
|
|
|
|
BTC = cleanNumbers(BTC) |
|
|
|
|
|
BTC = BTC.strip() |
|
|
|
|
|
|
|
|
# Finding Escrow - no escrow on WTN market |
|
|
# Finding Escrow - no escrow on WTN market |
|
|
|
|
|
|
|
|
shipping_info = listDes.find('tbody') |
|
|
shipping_info = listDes.find('tbody') |
|
|
@ -73,47 +69,32 @@ def wethenorth_description_parser(soup): |
|
|
|
|
|
|
|
|
# Finding Shipment Information (Origin) |
|
|
# Finding Shipment Information (Origin) |
|
|
shipFrom = row1[-1].text |
|
|
shipFrom = row1[-1].text |
|
|
shipFrom=shipFrom.strip() |
|
|
|
|
|
if shipFrom=="": |
|
|
|
|
|
shipFrom="-1" |
|
|
|
|
|
|
|
|
shipFrom = cleanString(shipFrom) |
|
|
|
|
|
shipFrom = shipFrom.strip() |
|
|
|
|
|
if shipFrom == "": |
|
|
|
|
|
shipFrom = "-1" |
|
|
|
|
|
|
|
|
row2 = shipping_info[1].find_all('td') |
|
|
row2 = shipping_info[1].find_all('td') |
|
|
|
|
|
|
|
|
# Finding Shipment Information (Destination) |
|
|
# Finding Shipment Information (Destination) |
|
|
shipTo = row2[-1].text |
|
|
shipTo = row2[-1].text |
|
|
shipTo= shipTo.strip() |
|
|
|
|
|
|
|
|
shipTo = cleanString(shipTo) |
|
|
|
|
|
shipTo = shipTo.strip() |
|
|
if shipTo == "": |
|
|
if shipTo == "": |
|
|
shipTo = "-1" |
|
|
shipTo = "-1" |
|
|
|
|
|
|
|
|
# Finding the Product description |
|
|
# Finding the Product description |
|
|
describe = soup.find("div",{'class':'tabcontent'}) |
|
|
|
|
|
|
|
|
describe = soup.find("div", {'class': 'tabcontent'}) |
|
|
describe = describe.find('p').text |
|
|
describe = describe.find('p').text |
|
|
describe = describe.replace("\n", " ") |
|
|
|
|
|
describe = describe.replace("\r", " ") |
|
|
|
|
|
|
|
|
describe = cleanString(describe) |
|
|
describe = describe.strip() |
|
|
describe = describe.strip() |
|
|
|
|
|
|
|
|
# cannot find any tag for these |
|
|
|
|
|
''' |
|
|
|
|
|
# Finding the Number of Product Reviews |
|
|
|
|
|
tag = soup.findAll(text=re.compile('Reviews')) |
|
|
|
|
|
for index in tag: |
|
|
|
|
|
reviews = index |
|
|
|
|
|
par = reviews.find('(') |
|
|
|
|
|
if par >=0: |
|
|
|
|
|
reviews = reviews.replace("Reviews (","") |
|
|
|
|
|
reviews = reviews.replace(")","") |
|
|
|
|
|
reviews = reviews.split(",") |
|
|
|
|
|
review = str(abs(int(reviews[0])) + abs(int(reviews[1]))) |
|
|
|
|
|
else : |
|
|
|
|
|
review = "-1" |
|
|
|
|
|
''' |
|
|
|
|
|
|
|
|
|
|
|
# Searching for CVE and MS categories |
|
|
# Searching for CVE and MS categories |
|
|
# no CVE or MS for WTN market |
|
|
# no CVE or MS for WTN market |
|
|
|
|
|
|
|
|
# Populating the final variable (this should be a list with all fields scraped) |
|
|
# Populating the final variable (this should be a list with all fields scraped) |
|
|
row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate, |
|
|
row = (vendor, rating_vendor, success, name, describe, CVE, MS, category, views, reviews, rating_item, addDate, |
|
|
BTC, USD, EURO, sold, left, shipFrom, shipTo) |
|
|
|
|
|
|
|
|
BTC, USD, EURO, sold, left, shipFrom, shipTo, image, vendor_image) |
|
|
|
|
|
|
|
|
# Sending the results |
|
|
# Sending the results |
|
|
return row |
|
|
return row |
|
|
@ -144,7 +125,9 @@ def wethenorth_listing_parser(soup): |
|
|
qLeft =[] # 17 Product_QuantityLeft |
|
|
qLeft =[] # 17 Product_QuantityLeft |
|
|
shipFrom = [] # 18 Product_ShippedFrom |
|
|
shipFrom = [] # 18 Product_ShippedFrom |
|
|
shipTo = [] # 19 Product_ShippedTo |
|
|
shipTo = [] # 19 Product_ShippedTo |
|
|
href = [] # 20 Product_Links |
|
|
|
|
|
|
|
|
image = [] # 20 Product_Image |
|
|
|
|
|
image_vendor = [] # 21 Vendor_Image |
|
|
|
|
|
href = [] # 22 Product_Links |
|
|
|
|
|
|
|
|
right_content = soup.find('div', {"class": "right-content"}) |
|
|
right_content = soup.find('div', {"class": "right-content"}) |
|
|
listing = right_content.findAll('div', {"class": "col-1search"}) |
|
|
listing = right_content.findAll('div', {"class": "col-1search"}) |
|
|
@ -158,20 +141,19 @@ def wethenorth_listing_parser(soup): |
|
|
|
|
|
|
|
|
# Adding the url to the list of urls |
|
|
# Adding the url to the list of urls |
|
|
link = bae[0].get('href') |
|
|
link = bae[0].get('href') |
|
|
link = cleanLink(link) |
|
|
|
|
|
href.append(link) |
|
|
href.append(link) |
|
|
|
|
|
|
|
|
# Finding the Vendor |
|
|
# Finding the Vendor |
|
|
vendor_name = a.find('p', {'class': 'padp'}) |
|
|
vendor_name = a.find('p', {'class': 'padp'}) |
|
|
vendor_name = vendor_name.find('a').text |
|
|
vendor_name = vendor_name.find('a').text |
|
|
vendor_name = vendor_name.replace(",", "") |
|
|
|
|
|
|
|
|
vendor_name = cleanString(vendor_name) |
|
|
vendor_name = vendor_name.strip() |
|
|
vendor_name = vendor_name.strip() |
|
|
vendor.append(vendor_name) |
|
|
vendor.append(vendor_name) |
|
|
|
|
|
|
|
|
# Finding the Product |
|
|
# Finding the Product |
|
|
product = bae[0].text |
|
|
|
|
|
product = product.replace('\n', ' ') |
|
|
|
|
|
product = product.replace(",", "") |
|
|
|
|
|
|
|
|
product = a.find('div', {'class': 'col-1centre'}) |
|
|
|
|
|
product = product.find('div', {'class': 'head'}).find('a').text |
|
|
|
|
|
product = cleanString(product) |
|
|
product = product.strip() |
|
|
product = product.strip() |
|
|
name.append(product) |
|
|
name.append(product) |
|
|
|
|
|
|
|
|
@ -179,25 +161,56 @@ def wethenorth_listing_parser(soup): |
|
|
category_name = a.find('p', {'class': 'padp'}).text |
|
|
category_name = a.find('p', {'class': 'padp'}).text |
|
|
first_dash = category_name.find('-') |
|
|
first_dash = category_name.find('-') |
|
|
second_dash = category_name[first_dash+1:].find('-') |
|
|
second_dash = category_name[first_dash+1:].find('-') |
|
|
category_name = category_name[first_dash+1:second_dash] |
|
|
|
|
|
category_name=category_name.strip() |
|
|
|
|
|
|
|
|
category_name = category_name[first_dash+1: first_dash + second_dash] |
|
|
|
|
|
category_name = cleanString(category_name) |
|
|
|
|
|
category_name = category_name.strip() |
|
|
category.append(category_name) |
|
|
category.append(category_name) |
|
|
|
|
|
|
|
|
|
|
|
# Finding Success Transactions |
|
|
|
|
|
vendor_success = a.find('p', {'class': 'padp'}).text |
|
|
|
|
|
first_dash = vendor_success.find('(') |
|
|
|
|
|
vendor_success = vendor_success[first_dash + 1:] |
|
|
|
|
|
vendor_success = cleanNumbers(vendor_success) |
|
|
|
|
|
vendor_success = vendor_success.strip() |
|
|
|
|
|
success.append(vendor_success) |
|
|
|
|
|
|
|
|
# Finding Views |
|
|
# Finding Views |
|
|
view_count = a.text |
|
|
view_count = a.text |
|
|
view_count = view_count[view_count.find('Views:'): view_count.find('Sales:')] |
|
|
view_count = view_count[view_count.find('Views:'): view_count.find('Sales:')] |
|
|
view_count = view_count.replace('Views:', ' ') |
|
|
view_count = view_count.replace('Views:', ' ') |
|
|
view_count = view_count.replace('/', ' ') |
|
|
|
|
|
|
|
|
view_count = cleanNumbers(view_count) |
|
|
view_count = view_count.strip() |
|
|
view_count = view_count.strip() |
|
|
views.append(view_count) |
|
|
views.append(view_count) |
|
|
|
|
|
|
|
|
# Finding success sales |
|
|
|
|
|
|
|
|
# Finding Quantity Sold |
|
|
sold_count = a.text |
|
|
sold_count = a.text |
|
|
sold_count = sold_count[sold_count.find('Sales:'): sold_count.find('Short')] |
|
|
sold_count = sold_count[sold_count.find('Sales:'): sold_count.find('Short')] |
|
|
sold_count = sold_count.replace('Sales:', ' ') |
|
|
sold_count = sold_count.replace('Sales:', ' ') |
|
|
sold_count = sold_count.replace('/', ' ') |
|
|
|
|
|
|
|
|
sold_count = cleanNumbers(sold_count) |
|
|
sold_count = sold_count.strip() |
|
|
sold_count = sold_count.strip() |
|
|
success.append(sold_count) |
|
|
|
|
|
|
|
|
sold.append(sold_count) |
|
|
|
|
|
|
|
|
|
|
|
right = a.find('div', {'class': 'col-1right'}) |
|
|
|
|
|
|
|
|
|
|
|
# Finding USD |
|
|
|
|
|
usd = right.find('a').text |
|
|
|
|
|
usd = "CAD " + usd.strip() |
|
|
|
|
|
USD.append(usd) |
|
|
|
|
|
|
|
|
|
|
|
# Finding BTC |
|
|
|
|
|
btc = right.text |
|
|
|
|
|
first_dash = btc.find('(') |
|
|
|
|
|
second_dash = btc[first_dash + 1:].find(')') |
|
|
|
|
|
btc = btc[first_dash + 1: first_dash + second_dash] |
|
|
|
|
|
btc = cleanNumbers(btc) |
|
|
|
|
|
btc = btc.strip() |
|
|
|
|
|
BTC.append(btc) |
|
|
|
|
|
|
|
|
|
|
|
# Finding Product Image |
|
|
|
|
|
product_image = right.find('img') |
|
|
|
|
|
product_image = product_image.get('src') |
|
|
|
|
|
product_image = product_image.split('base64,')[-1] |
|
|
|
|
|
image.append(product_image) |
|
|
|
|
|
|
|
|
# Searching for CVE and MS categories |
|
|
# Searching for CVE and MS categories |
|
|
# no CVE or MS in WTN market |
|
|
# no CVE or MS in WTN market |
|
|
@ -229,7 +242,7 @@ def wethenorth_listing_parser(soup): |
|
|
|
|
|
|
|
|
# Populate the final variable (this should be a list with all fields scraped) |
|
|
# Populate the final variable (this should be a list with all fields scraped) |
|
|
return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views, |
|
|
return organizeProducts(mktName, nm, vendor, rating_vendor, success, name, CVE, MS, category, describe, views, |
|
|
reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href) |
|
|
|
|
|
|
|
|
reviews, rating_item, addDate, BTC, USD, EURO, sold, qLeft, shipFrom, shipTo, href, image, image_vendor) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def wethenorth_links_parser(soup): |
|
|
def wethenorth_links_parser(soup): |
|
|
|
Helium
11 months ago