import numpy as np
np.random.seed(42)
import requests
from bs4 import BeautifulSoup
url = 'https://quotes.toscrape.com/'
html = requests.get(url).text
soup = BeautifulSoup(html, 'html.parser')
quotes = [q.get_text(strip=True) for q in soup.select('.quote span.text')][:5]
print(quotes)

# Suppress warnings for a smooth beginner experience
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)
 

# Data setup: Scraping YouTube channel video titles using RSS
import feedparser
channel_id = 'UCYO_jab_esuFRV4b17AJtAw'  # 3Blue1Brown, an educational channel
feed_url = f'https://www.youtube.com/feeds/videos.xml?channel_id={channel_id}'
feed = feedparser.parse(feed_url)
titles = [entry.title for entry in feed.entries[:5]]
print(titles)
 

# Previewing our data
for i, title in enumerate(titles, 1):
    print(f"{i}. {title}")
 

# Why do we only take five titles?
# This is for speed and simplicity.
# With more experience, you can explore larger samples.
 

# Turn titles list into a DataFrame for easy analysis
import pandas as pd
df = pd.DataFrame({'Title': titles})
print(df.shape)
print(df.head())
 

# Check for empty or broken titles
print(df[ df['Title'].isnull() | (df['Title'].str.strip() == "") ])
 

# Clean up extra spaces or weird characters
df['Title'] = df['Title'].str.strip()
 

# Make all words lowercase and split into words
all_words = ' '.join(df['Title']).lower().split()
print(all_words)
 

# Count the frequency of each word in the titles
from collections import Counter
word_counts = Counter(all_words)
print(word_counts.most_common(5))
 

# Show bar plot of frequent words using matplotlib
import matplotlib.pyplot as plt
top_words = word_counts.most_common(5)
words, counts = zip(*top_words)
plt.figure(figsize=(8,4))
plt.bar(words, counts, color='skyblue')
plt.title('Most Common Words in Video Titles')
plt.xlabel('Word')
plt.ylabel('Count')
plt.show()
 

# Find the longest video title
longest_idx = df['Title'].str.len().idxmax()
print('Longest title:', df.loc[longest_idx, 'Title'])
 

# Interactive: Try searching for a word in video titles
search_word = input("Type a word to search in titles:").strip().lower()
matches = df[ df['Title'].str.lower().str.contains(search_word) ]
print(matches)
 

# Extra: How to find a YouTube channel's ID
print("Go to the YouTube channel. In the URL, look for 'channel/UC...'. Copy the long code after '/channel/'.")
 

# Let us celebrate! You have just built your first YouTube scraper.
print("Great job! You collected and analyzed public YouTube video data.")
print("Consider subscribing if you want more beginner friendly Python and data lessons!")