amazon-analysis/amazon_scrapper.py at main · sarasakeena/amazon-analysis · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
import pandas as pd #type: ignore

# Sample Amazon Soft Toy Data
data = {
    "Title": [
        "Teddy Bear", "Plush Puppy", "Cute Bunny", "Elephant Soft Toy", "Cartoon Lion",
        "Panda Soft Toy", "Dinosaur Plush", "Rabbit Cuddle Toy", "Unicorn Plush", "Cat Plush",
        "Monkey Toy", "Disney Mickey Plush", "Cuddly Koala", "Giant Teddy Bear", "Mini Teddy Set",
        "Fox Plush", "Baby Yoda Plush", "Penguin Soft Toy", "Superhero Plush", "Huggable Polar Bear",
        "Disney Donald Plush", "Dolphin Soft Toy", "Crocodile Plush", "Duck Cuddle Toy", "Star Wars Plush",
        "Marvel Character Plush", "Elephant Pillow Toy", "Owl Plush", "Cute Hamster Plush", "Sleeping Bear Toy"
    ],
    "Brand": [
        "ToyBrand1", "ToyBrand2", "ToyBrand3", "ToyBrand4", "ToyBrand5",
        "ToyBrand6", "ToyBrand7", "ToyBrand8", "ToyBrand9", "ToyBrand10",
        "ToyBrand11", "ToyBrand12", "ToyBrand13", "ToyBrand14", "ToyBrand15",
        "ToyBrand16", "ToyBrand17", "ToyBrand18", "ToyBrand19", "ToyBrand20",
        "ToyBrand21", "ToyBrand22", "ToyBrand23", "ToyBrand24", "ToyBrand25",
        "ToyBrand26", "ToyBrand27", "ToyBrand28", "ToyBrand29", "ToyBrand30"
    ],
    "Reviews": [1500, 850, 1200, 650, 900, 2500, 300, 1100, 700, 1800,
                1300, 400, 600, 5000, 750, 450, 3000, 1250, 950, 800,
                900, 2000, 650, 550, 850, 400, 1100, 2750, 375, 920],
    "Rating": [4.5, 4.2, 4.8, 4.3, 4.6, 4.9, 4.1, 4.7, 4.4, 4.5,
               4.3, 4.0, 4.6, 4.9, 4.2, 4.8, 5.0, 4.3, 4.6, 4.7,
               4.4, 4.2, 4.3, 4.1, 4.5, 4.0, 4.7, 4.8, 4.3, 4.6],
    "Price": [499, 349, 599, 799, 399, 999, 299, 699, 549, 450,
              899, 650, 750, 1500, 450, 620, 2000, 875, 920, 770,
              800, 1100, 550, 490, 950, 600, 750, 1200, 399, 875],
    "Image URL": [f"https://example.com/image{i}.jpg" for i in range(1, 31)],
    "Product URL": [f"https://example.com/product{i}" for i in range(1, 31)]
}

# Convert to DataFrame
df = pd.DataFrame(data)

# Save as CSV
df.to_csv("amazon_products.csv", index=False)

print(" CSV file 'amazon_products.csv' created successfully!")