Quickstart

python scraping5.py

import instaloader
import csv

# Create an instance of Instaloader
L = instaloader.Instaloader()

# Instagram profile name
profile_name = "historiaparagandules"

# Get the profile
profile = instaloader.Profile.from_username(L.context, profile_name)

# Create CSV file
with open("informacion_reels_simple.csv", mode="w", newline="", encoding="utf-8") as file:
    writer = csv.writer(file)
    writer.writerow(["Fecha", "Texto del reel", "Likes", "Comentarios", "URL del video", 
                     "Visualizaciones", "Duración del video (s)", "URL del Post"])

    # Iterate over posts and write to CSV
    for post in profile.get_posts():
        if post.is_video:  # Filter only videos
            fecha = post.date.strftime('%Y-%m-%d %H:%M:%S')
            texto = post.caption or "Sin texto"
            likes = post.likes or 0
            comentarios = post.comments or 0
            url_video = post.video_url or "Sin URL"
            visualizaciones = post.video_view_count or "No disponible"
            duracion_video = post.video_duration or "No disponible"
            url_post = f"https://www.instagram.com/p/{post.shortcode}/"

            writer.writerow([fecha, texto, likes, comentarios, url_video, 
                             visualizaciones, duracion_video, url_post])
            print(f"Scrapeando post del {fecha}")

print("Información guardada en 'informacion_reels_simple.csv'")

python mapita5.py

import folium
import pandas as pd
import requests
import os

# Create directory for images
if not os.path.exists("imagenes"):
    os.makedirs("imagenes")

# Load the Excel file
df = pd.read_excel('excel_info_1.xlsx')

# Function to get coordinates
def obtener_coordenadas(localizacion):
    try:
        lat, lon = map(float, localizacion.split(','))
        return lat, lon
    except Exception as e:
        print(f"Error al procesar la ubicación: {localizacion} - {e}")
        return None, None

# Download and store images locally
def descargar_imagen(url, index):
    try:
        response = requests.get(url, stream=True)
        if response.status_code == 200:
            ruta_imagen = f"imagenes/imagen_{index}.jpg"
            with open(ruta_imagen, 'wb') as file:
                for chunk in response.iter_content(1024):
                    file.write(chunk)
            return ruta_imagen
        else:
            print(f"No se pudo descargar la imagen: {url}")
            return None
    except Exception as e:
        print(f"Error al descargar la imagen: {url} - {e}")
        return None

# Create the map
m = folium.Map(location=[28.0, -15.0], zoom_start=6)

# Iterate over the DataFrame
for index, row in df.iterrows():
    lat, lon = obtener_coordenadas(row['Localización'])
    if lat is not None and lon is not None:
        ruta_imagen = descargar_imagen(row['URL de imagen'], index)
        if ruta_imagen:
            popup_content = f"""
            <div>
                <h4>{row['Texto del reel'].split(' ')[0]}</h4>
                <img src="{ruta_imagen}" alt="Imagen del Reel" style="width:200px;height:auto;">
                <a href="{row['URL del Post']}">Ver publicación</a>
            </div>
            """
            folium.Marker(
                location=[lat, lon],
                popup=folium.Popup(popup_content, max_width=300),
            ).add_to(m)

# Save the map as an HTML file
m.save("mapa_ubicaciones_reels_with_thumbnails.html")
print("Mapa generado con imágenes y enlaces: 'mapa_ubicaciones_reels_with_thumbnails.html'")

# macOS
open mapa_ubicaciones_reels_with_thumbnails.html

# Linux
xdg-open mapa_ubicaciones_reels_with_thumbnails.html

# Windows
start mapa_ubicaciones_reels_with_thumbnails.html

jupyter notebook EDA.ipynb

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Load data
df = pd.read_excel('excel26deenero.xlsx')

# Descriptive statistics
print("Estadísticas Descriptivas:")
print(df[['Likes', 'Comentarios', 'Visualizaciones', 'Duración del video (s)']].describe())

# Top 5 videos by likes
top_5_likes = df[['Texto del reel', 'Likes', 'Comentarios', 'Visualizaciones']].sort_values(
    by='Likes', ascending=False
).head(5)

print("\nTop 5 videos con más Likes:")
print(top_5_likes)

# 1. Scrape data
python scraping5.py

# 2. Generate map
python mapita5.py

# 3. Launch analysis
jupyter notebook EDA.ipynb

import pandas as pd

df = pd.read_excel('excel26deenero.xlsx')

# Export to CSV
df.to_csv('analysis_results.csv', index=False)

# Export summary statistics
df.describe().to_csv('summary_stats.csv')