manage exception when no description
This commit is contained in:
parent
2bbf684c26
commit
4247f1ac83
@ -32,8 +32,13 @@ def get_image_url(soup, url):
|
|||||||
|
|
||||||
# get full description as string
|
# get full description as string
|
||||||
# luckily this <p> was the only one without class
|
# luckily this <p> was the only one without class
|
||||||
|
# and manage the case where there's no description
|
||||||
def product_description(soup):
|
def product_description(soup):
|
||||||
desc = soup.find("p", class_='').string
|
try:
|
||||||
|
desc = soup.find("p", class_='').string
|
||||||
|
except AttributeError:
|
||||||
|
desc = "None"
|
||||||
|
|
||||||
return desc
|
return desc
|
||||||
|
|
||||||
# get category from breadcrumb
|
# get category from breadcrumb
|
||||||
@ -44,16 +49,19 @@ def get_category(soup):
|
|||||||
# create a list with all information consecutively
|
# create a list with all information consecutively
|
||||||
# /!\ don't know if that's the best way
|
# /!\ don't know if that's the best way
|
||||||
def get_data(soup, url):
|
def get_data(soup, url):
|
||||||
info = [url, product_information(soup)['UPC'],
|
info = [
|
||||||
get_title(soup),
|
url, product_information(soup)['UPC'],
|
||||||
product_information(soup)['Price (incl. tax)'],
|
get_title(soup),
|
||||||
product_information(soup)['Price (excl. tax)'],
|
product_information(soup)['Price (incl. tax)'],
|
||||||
product_information(soup)['Availability'],
|
product_information(soup)['Price (excl. tax)'],
|
||||||
product_description(soup),
|
product_information(soup)['Availability'],
|
||||||
get_category(soup),
|
product_description(soup),
|
||||||
product_information(soup)['Number of reviews'],
|
get_category(soup),
|
||||||
get_image_url(soup, url)
|
product_information(soup)['Number of reviews'],
|
||||||
]
|
get_image_url(soup, url)
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
return info
|
return info
|
||||||
|
|
||||||
# write the file
|
# write the file
|
||||||
@ -76,6 +84,7 @@ def data_output(info, file):
|
|||||||
for i in info:
|
for i in info:
|
||||||
writer.writerow(i)
|
writer.writerow(i)
|
||||||
|
|
||||||
|
return file
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user