data_scraping.py

"""Mini data scraping project: scrape quotes and save to CSV."""

import csv                              # built-in module for reading/writing CSV files
import requests                         # library to download web pages (send HTTP requests)
from bs4 import BeautifulSoup           # parses HTML so we can search it easily

# URL template; the {} gets replaced with a page number (page 1, 2, 3...)
BASE_URL = "https://quotes.toscrape.com/page/{}/"


def scrape():                          # function that gathers all quotes and returns them
    rows = []                          # empty list to hold each quote as a dictionary
    page = 1                           # page counter, starts at page 1
    while True:                        # loop forever until we 'break' out of it
        # fill {} with current page number, download it, give up after 10 seconds
        resp = requests.get(BASE_URL.format(page), timeout=10)
        # turn the raw HTML text into a searchable object
        soup = BeautifulSoup(resp.text, "html.parser")
        quotes = soup.select(".quote")  # find every element with class "quote" (a list)
        if not quotes:                 # if the list is empty, there are no more pages
            break                      # exit the while loop
        for q in quotes:               # loop over each quote block on this page
            rows.append({              # build a dictionary and add it to rows
                # find the .text element inside q, get its text, trim whitespace
                "text": q.select_one(".text").get_text(strip=True),
                # same for the author's name
                "author": q.select_one(".author").get_text(strip=True),
                # collect all .tag elements and join their text into one string
                "tags": ", ".join(t.get_text() for t in q.select(".tag")),
            })
        print(f"Scraped page {page} ({len(quotes)} quotes)")  # progress message
        page += 1                      # move to the next page
    return rows                        # hand back the full list of quotes


def save(rows, filename="quotes.csv"):  # write the list of quotes to a CSV file
    # open the file for writing; utf-8 handles special characters
    with open(filename, "w", newline="", encoding="utf-8") as f:
        # writer that converts dictionaries into CSV rows; sets column order
        writer = csv.DictWriter(f, fieldnames=["text", "author", "tags"])
        writer.writeheader()           # write the header row (column titles)
        writer.writerows(rows)         # write every quote as its own line
    print(f"Saved {len(rows)} quotes to {filename}")  # confirmation message


if __name__ == "__main__":             # runs only when the file is executed directly
    save(scrape())                     # scrape the quotes, then save them to CSV