added all defs to main def
This commit is contained in:
parent
f40825139b
commit
869a4613fb
18
posh.py
18
posh.py
@ -7,7 +7,9 @@ import numpy as np
|
||||
# import matplotlib.pyplot as plt
|
||||
|
||||
|
||||
def url_base_builder(search_query):
|
||||
def main():
|
||||
|
||||
def url_base_builder(search_query):
|
||||
genders = ['Men', 'Women']
|
||||
|
||||
posh_colors = ['Red', 'Pink', 'Orange', 'Yellow', 'Green', 'Blue', 'Purple',
|
||||
@ -41,7 +43,7 @@ def url_base_builder(search_query):
|
||||
return all_sold_url_base, new_sold_url_base
|
||||
|
||||
|
||||
def all_sold_list_builder(i):
|
||||
def all_sold_list_builder(i):
|
||||
bases = url_base_builder(search_query)
|
||||
all_sold_url_base = bases[0]
|
||||
all_sold_prices = []
|
||||
@ -59,7 +61,7 @@ def all_sold_list_builder(i):
|
||||
return all_sold_prices
|
||||
|
||||
|
||||
def new_sold_list_builder(i):
|
||||
def new_sold_list_builder(i):
|
||||
bases = url_base_builder(search_query)
|
||||
new_sold_url_base = bases[1]
|
||||
new_sold_prices = []
|
||||
@ -77,14 +79,11 @@ def new_sold_list_builder(i):
|
||||
new_sold_prices.append(price)
|
||||
return new_sold_prices
|
||||
|
||||
|
||||
def main():
|
||||
|
||||
search_query = str(input('Title Search: '))
|
||||
|
||||
start = time.time()
|
||||
|
||||
page_list = list(range(1, 2))
|
||||
page_list = list(range(1, 5))
|
||||
all_sold_list = []
|
||||
new_sold_list = []
|
||||
|
||||
@ -116,5 +115,8 @@ def main():
|
||||
print('Average New Sold Price', average_new_sold_price, new_sold_results)
|
||||
print(total_results)
|
||||
|
||||
main()
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
||||
|
||||
'''to speed up the program you can include a few things: 1) only parse the total results and sift for the NWT listings to create a separate NWT list 2) Implement processpoolexecutor to use more than one worker to parse the pages 3) find a better way to find the last page so you don't have to make more requests than necessary. This could be either taking the "smallest" "no listings found" page of the pages while excluding the others after the smallest one is found. Or, determining from the request headers whether a page is worth downloading or not 4) using a while loop in chunks of 2-4 pages to find the last page in conjunction with number 3'''
|
Loading…
Reference in New Issue
Block a user