173 lines
6.4 KiB
Python
173 lines
6.4 KiB
Python
import seaborn as sns
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
import re
|
|
# import bs4
|
|
from bs4 import BeautifulSoup as b
|
|
import requests
|
|
import time
|
|
|
|
# Initial Search Query URL to Find ItemCondition Code
|
|
while True:
|
|
print("Title Search:")
|
|
|
|
start = time.time()
|
|
|
|
SQ = str(input())
|
|
SQ_1 = SQ.replace(' ', '+').replace('NEW',
|
|
'').replace('men', '').replace('women', '')
|
|
gender = ['Men', 'Women']
|
|
|
|
# &color[]=color
|
|
posh_colors = ['Red', 'Pink', 'Orange', 'Yellow', 'Green', 'Blue', 'Purple',
|
|
'Gold', 'Silver', 'Black', 'Gray', 'White', 'Cream', 'Brown', 'Tan']
|
|
|
|
for i in range(0, len(posh_colors)):
|
|
if posh_colors[i] in SQ:
|
|
url_color = '&color[]=' + posh_colors[i]
|
|
url_separator = "&availability=sold_out" + url_color + "&department=All&max_id="
|
|
url_separator1 = "&availability=sold_out" + url_color + \
|
|
"&condition=nwt_and_ret&department=All&max_id="
|
|
SQ_1 = SQ_1.replace(posh_colors[i], '')
|
|
break
|
|
else:
|
|
url_separator = "&availability=sold_out&department=All&max_id="
|
|
url_separator1 = "&availability=sold_out&condition=nwt_and_ret&department=All&max_id="
|
|
|
|
prices = []
|
|
prices1 = []
|
|
base_url = "https://poshmark.com/search?query="
|
|
|
|
pg = 1
|
|
url = base_url + SQ_1 + url_separator + str(pg)
|
|
url_1 = base_url + SQ_1 + url_separator1 + str(pg)
|
|
url_a = base_url + SQ_1 + url_separator + str(pg)
|
|
url_1b = base_url + SQ_1 + url_separator1 + str(pg)
|
|
|
|
html = requests.get(url).text
|
|
html1 = requests.get(url_1).text
|
|
soup = b(html, "lxml")
|
|
soup1 = b(html1, 'lxml')
|
|
|
|
# Begin new and used condition items price list:
|
|
|
|
for listing in soup.findAll("div", {"class": "item__details"}):
|
|
price = listing.findAll("span", {"class": "p--t--1 fw--bold"})[0].text
|
|
indices = price.find('$')
|
|
price = price[indices + 1:]
|
|
space = price.find(' ')
|
|
price = int(price[:space - 1])
|
|
prices.append(price)
|
|
|
|
while True:
|
|
last_page = soup.find_all(string=re.compile('No Listings Found'))
|
|
if last_page:
|
|
break
|
|
pg = pg + 1
|
|
url = base_url + SQ_1 + url_separator + str(pg)
|
|
html = requests.get(url).text
|
|
soup = b(html, "lxml")
|
|
|
|
for listing in soup.findAll("div", {"class": "item__details"}):
|
|
price = listing.findAll(
|
|
"span", {"class": "p--t--1 fw--bold"})[0].text
|
|
# indices = [i for i, dollars in enumerate(price) if dollars == '$']
|
|
# price = int(price[1:indices[1]-1])
|
|
indices = price.find('$')
|
|
price = price[indices + 1:]
|
|
space = price.find(' ')
|
|
price = int(price[:space - 1])
|
|
prices.append(price)
|
|
|
|
# Begin new condition item prices list:
|
|
|
|
for listing in soup1.findAll("div", {"class": "item__details"}):
|
|
price1 = listing.findAll("span", {"class": "p--t--1 fw--bold"})[0].text
|
|
# indices = [i for i, dollars in enumerate(price1) if dollars == '$']
|
|
# price1 = int(price1[1:indices[1]-1])
|
|
indices = price1.find('$')
|
|
price1 = price1[indices + 1:]
|
|
space = price1.find(' ')
|
|
price1 = int(price1[:space - 1])
|
|
prices1.append(price1)
|
|
|
|
while True:
|
|
|
|
last_page = soup1.find_all(string=re.compile('No Listings Found'))
|
|
if last_page:
|
|
break
|
|
pg = pg + 1
|
|
url_1 = base_url + SQ_1 + url_separator1 + str(pg)
|
|
html1 = requests.get(url_1).text
|
|
soup1 = b(html1, "lxml")
|
|
|
|
for listing in soup1.findAll("div", {"class": "item__details"}):
|
|
price1 = listing.findAll(
|
|
"span", {"class": "p--t--1 fw--bold"})[0].text
|
|
# indices = [i for i, dollars in enumerate(price1) if dollars == '$']
|
|
# price1 = int(price1[1:indices[1]-1])
|
|
indices = price1.find('$')
|
|
price1 = price1[indices + 1:]
|
|
space = price1.find(' ')
|
|
price1 = int(price1[:space - 1])
|
|
prices1.append(price1)
|
|
|
|
# Begin Element-wise substraction of new condition items price list from new&used items price list:
|
|
print(len(prices), 'NEW & USED')
|
|
print(len(prices1), 'NEW')
|
|
|
|
end = time.time()
|
|
|
|
print(end - start)
|
|
|
|
for element in prices1:
|
|
prices.remove(element)
|
|
|
|
if 'NEW' in SQ:
|
|
kde_datapoints = sns.kdeplot(prices1, shade=True).get_lines()[
|
|
0].get_data()
|
|
sns.rugplot(prices1)
|
|
print(str(len(prices1)) + " Results" + "\n")
|
|
print("Average Price Sold New = $" + str(np.mean(prices1)) + "\n")
|
|
total_price = np.mean(prices1) + 6.79
|
|
print("Average Total Price New = $" + str(total_price) + "\n")
|
|
print("Flat Rate Shipping = $6.79" + "\n")
|
|
|
|
kde_x = kde_datapoints[0]
|
|
kde_y = kde_datapoints[1]
|
|
optimal_price = kde_x[np.argmax(kde_y)]
|
|
print("Optimal Price New = $" + str(optimal_price) + "\n")
|
|
print("Optimal Price Including Shipping New = $" +
|
|
str(optimal_price + 6.79) + "\n")
|
|
print("URL Link (New): " + url_1b + "\n")
|
|
plt.ylabel('KDE')
|
|
plt.xlabel('Price ($)')
|
|
plt.show()
|
|
else:
|
|
try:
|
|
|
|
kde_datapoints = sns.kdeplot(prices, shade=True).get_lines()[
|
|
0].get_data()
|
|
sns.rugplot(prices)
|
|
print(str(len(prices)) + " Results" + "\n")
|
|
print("Average Price Sold Used = $" + str(np.mean(prices)) + "\n")
|
|
total_price = np.mean(prices) + 6.79
|
|
print("Average Total Price Used = $" + str(total_price) + "\n")
|
|
print("Flat Rate Shipping = $6.79" + "\n")
|
|
import winsound
|
|
winsound.Beep(440, 300)
|
|
|
|
kde_x = kde_datapoints[0]
|
|
kde_y = kde_datapoints[1]
|
|
optimal_price = kde_x[np.argmax(kde_y)]
|
|
print("Optimal Price Used = $" + str(optimal_price) + "\n")
|
|
print("Optimal Price Including Shipping Used = $" +
|
|
str(optimal_price + 6.79) + "\n")
|
|
print("URL Link: " + url_a + "\n")
|
|
plt.ylabel('KDE')
|
|
plt.xlabel('Price ($)')
|
|
plt.show()
|
|
except IndexError:
|
|
print('\n' + '0 results' + '\n')
|
|
pass
|