edwards

import requests
from tqdm import tqdm
import pandas as pd
from bs4 import BeautifulSoup



RESULT = []
url = 'https://www.constructionequipmentguide.com/used-excavators-for-sale/'

r = requests.get(url)
soup = BeautifulSoup(r.text, "html.parser")
type_ul_tags = soup.find("ul", class_="columns-three")
links = [item.find("a").get("href") for item in type_ul_tags.findAll("li")]
subtypes = [item.find("a").text for item in type_ul_tags.findAll("li")]
links = ["https://www.constructionequipmentguide.com"+item for item in links]


def get_equipment_details(listing, subtype):
    obj = {}

    try:
        model = listing.find("div", class_="machine-model").find("a").text.strip()
    except Exception as e:
        model = None

    try:
        year = listing.find("div", class_="machine-model").find("a").text.strip().split(" ")[0].strip()
    except Exception as e:
        year = None

    try:
        dealer =  listing.find("div", class_="machine-contact").find("div", class_="machine-dealer").text.strip()
    except Exception as e:
        dealer = None

    try:
        price = listing.find("div", class_="machine-details").find("div", class_="machine-price").text.strip()
    except Exception as e:
        price = None

    try:
        currency = price.split(" ")[-1].strip() if price else None
    except Exception as e:
        currency = None

    try:
        serial_no = listing.find("div", class_="machine-details").find("div", class_="machine-serial-stock").text.strip().replace("Serial:", "").strip()
    except Exception as e:
        serial_no = None

    try:
        url = listing.find("div", class_="machine-model").find("a").get("href")
        url = "https://www.constructionequipmentguide.com"+url
    except Exception as e:
        url = None
        print(e)

    obj["Model"] = model
    obj["Year"] = year
    obj["Seller_Name"] = dealer
    obj["Price"] = price
    obj["Currency"] = currency if currency != 'Price' else None
    obj["Serial_Number"] = serial_no
    obj["URL"] = url
    obj["SubType"] = subtype
    obj["Manufacturer"] = None

    if url:
        more_details = get_more_details(url)
        obj_joined = {**obj, **more_details}

    return obj_joined


def get_more_details(url):
    obj = {}
    r = requests.get(url)
    soup = BeautifulSoup(r.text, "html.parser")

    try:
        condition_check = soup.find("div", class_="meta-descriptions").find("tr", class_="categories").find("td").\
        text.strip()
        if condition_check == "Condition":
            condition= soup.find("div", class_="meta-descriptions").findAll("tr")[1].findAll("td")[1].\
        text.strip()

        else:
            condition = None
    except Exception as e:
        condition = None

    try:
        size_class = None
        table = soup.find("table", class_="category-specs")  #.findAll("tr")
        for row in table.findAll("tr"):
            if "Power" in row.find("td").text.strip():
                size_class = row.findAll("td")[1].text.strip()
                break

    except Exception as e:
        size_class = None
        #print(e)

    try:
        category = soup.find("span", {"content": "3"}).text.strip()
    except Exception as e:
        category = None

    try:
        zip = soup.find("table", class_="machine-info").find("tr", class_="machine-location").findAll("td")[-1].\
    text.split(" ")[-1].strip()

    except Exception as e:
        zip = None

    try:
        state = soup.find("table", class_="machine-info").find("tr", class_="machine-location").findAll("td")[-1].\
        text.split(" ")[1].replace(",", "").strip()
    except Exception as e:
        state = None

    try:
        city = soup.find("table", class_="machine-info").find("tr", class_="machine-location").findAll("td")[-1].\
        text.split(" ")[0].strip()
    except Exception as e:
        city = None

    obj["Category"] = category
    obj["Condition"] = condition
    obj["Size_Class"] = size_class
    obj["Seller_Zip"] = zip
    obj["Seller_State"] = state
    obj["Seller_City"] = city
    obj["Seller_Country"] = None
    obj["Meter_Reads"] = None
    obj["Meter_Reads_UOM"] = None

    return obj



for index, link in enumerate(links[0:]):
    r = requests.get(link)
    soup = BeautifulSoup(r.text, "html.parser")
    for page_num in range(1, 500):
        r = requests.get(f"https://www.constructionequipmentguide.com/used-excavators-for-sale/all/type/large-excavators/{page_num}")
        soup = BeautifulSoup(r.text, "html.parser")
        try:
            big_paragraph = soup.find("p", class_="larger-text").text.strip()
            check_page_invalid = "We currently don't have any equipment listed for this type of machine." == big_paragraph
            if check_page_invalid:
                break
        except Exception as e:
            print(e)
            pass

        for listing in tqdm(soup.findAll("div", class_="machine-listing")):
            listing_item = get_equipment_details(listing=listing, subtype=subtypes[index])
            RESULT.append(listing_item)


df = pd.DataFrame(RESULT)
df.to_csv("result.csv", index=False)