bb_extractor.py

# this is from the bluebook bike website
# thre is a html file with the bike listings that i parse from this
# Tim Booher - May 26, 2025

from bs4 import BeautifulSoup
import pandas as pd

# Load the HTML content from file
with open("data/page.html", "r", encoding="utf-8") as f:
    soup = BeautifulSoup(f, "html.parser")

# Extract all product cards
cards = soup.select("div.product_gridView__fxpIW")

# Parse relevant data
data = []
for card in cards:
    name_tag = card.select_one("h5.product_bikeName__g3kKC")
    type_tag = card.select_one("p.product_bikeType__3xlXW")
    price_tag = card.select_one("p.product_bikePrice__S7rBh")

    if name_tag and type_tag and price_tag:
        name = name_tag.get_text(strip=True)
        bike_type, size = map(str.strip, type_tag.get_text().split("●"))
        price = price_tag.get_text(strip=True).replace("$", "").replace(",", "")
        data.append((name, bike_type, size, price))

# Convert to DataFrame and save as TSV
df = pd.DataFrame(data, columns=["Name", "Type", "Size", "Price"])
df.to_csv("bikes.tsv", sep="\t", index=False)

print(f"Extracted {len(df)} bike listings to bikes.tsv")