Create app.py

app.py

@@ -0,0 +1,191 @@
+import requests
+import pandas as pd
+
+def scrape_instagram(user_name):
+
+    url = "https://instagram-scraper-api2.p.rapidapi.com/v1/info"
+    
+    querystring = {"username_or_id_or_url":f"{user_name}"}
+    
+    headers = {
+    	"x-rapidapi-key": f"{RAPIDAPI_API_KEY}",
+    	"x-rapidapi-host": "instagram-scraper-api2.p.rapidapi.com"
+    }
+    
+    response = requests.get(url, headers=headers, params=querystring)
+
+    if response.status_code != 200:
+        print(f"Failed to fetch profile: {response.status_code}")
+        return {}  # Return an empty dictionary if the request fails
+
+    response_json = response.json()
+    if 'data' not in response_json:
+        print("No data found in response")
+        return {}  # Return an empty dictionary if there is no data in the response
+    
+    response_data = response_json['data']
+    
+    profile_info = {
+        'bio': response_data.get('biography', ''),
+        'follower_count': response_data.get('follower_count', 0),
+        'following_count': response_data.get('following_count', 0),
+        'bio_links': [item['url'] for item in response_data.get('bio_links', [])],
+        'full_name': response_data.get('full_name', ''),
+        'username': response_data.get('username', ''),
+        'num_posts': response_data.get('media_count', 0),
+        'profile_id': response_data.get('profile_pic_id', ''),
+        'email': response_data.get('biography_email', ''),
+        'badge': response_data.get('account_badges', []),
+        'category': response_data.get('category', ''),
+        'phone_number': response_data.get('contact_phone_number', ''),
+        'city_name': response_data.get('location_data', {}).get('city_name', ''),
+        'country': response_data.get('about', {}).get('country', ''),
+        'date_joined': response_data.get('about', {}).get('date_joined', '')
+    }
+
+    return profile_info
+
+def get_insta_info(df):
+    # Add new columns to the DataFrame
+    df['Bio'] = ''
+    df['Follower Count'] = 0
+    df['Following Count'] = 0
+    df['Bio Links'] = ''
+    df['Full Name'] = ''
+    df['Username'] = ''
+    df['Num Posts'] = 0
+    df['Profile ID'] = ''
+    df['Email'] = ''
+    df['Badge'] = ''
+    df['Category'] = ''
+    df['Phone Number'] = ''
+    df['City Name'] = ''
+    df['Country'] = ''
+    df['Date Joined'] = ''
+    
+    for index, row in df.iterrows():
+        profile_info = scrape_instagram(row['Username'])
+        
+        if profile_info:  # Only populate if profile_info is not empty
+            df.at[index, 'Bio'] = profile_info['bio']
+            df.at[index, 'Follower Count'] = profile_info['follower_count']
+            df.at[index, 'Following Count'] = profile_info['following_count']
+            df.at[index, 'Bio Links'] = ', '.join(profile_info['bio_links'])
+            df.at[index, 'Full Name'] = profile_info['full_name']
+            df.at[index, 'Username'] = profile_info['username']
+            df.at[index, 'Num Posts'] = profile_info['num_posts']
+            df.at[index, 'Profile ID'] = profile_info['profile_id']
+            df.at[index, 'Email'] = profile_info['email']
+            df.at[index, 'Badge'] = ', '.join(profile_info['badge'])
+            df.at[index, 'Category'] = profile_info['category']
+            df.at[index, 'Phone Number'] = profile_info['phone_number']
+            df.at[index, 'City Name'] = profile_info['city_name']
+            df.at[index, 'Country'] = profile_info['country']
+            df.at[index, 'Date Joined'] = profile_info['date_joined']
+    
+    return df
+
+# Function to scrape LinkedIn profiles
+def scrape_linkedins(links):
+    url = "https://linkedin-bulk-data-scraper.p.rapidapi.com/profiles"
+    
+    payload = {"links": links}
+    
+    headers = {
+        "x-rapidapi-key": f"{RAPIDAPI_API_KEY}",
+        "x-rapidapi-host": "linkedin-bulk-data-scraper.p.rapidapi.com",
+        "Content-Type": "application/json",
+        "x-rapidapi-user": "usama"
+    }
+
+    # Initialize an empty list to store the dictionaries
+    profile_info_list = []
+    
+    response = requests.post(url, json=payload, headers=headers)
+    responses = response.json()['data']
+    for response_item in responses:
+        response_data = response_item.get('data', {})
+        
+        # Use get() method with default empty strings for missing fields
+        profile_info = {
+            'full_name': response_data.get('fullName', ''),
+            'headline': response_data.get('headline', ''),
+            'connections': response_data.get('followers', ''),  # or 'connections' based on availability
+            'country': response_data.get('addressCountryOnly', ''),
+            'address': response_data.get('addressWithoutCountry', ''),
+            'about': response_data.get('about', ''),
+            'current_role': (f"{response_data.get('experiences', [{}])[0].get('title', '')} at "
+                             f"{response_data.get('experiences', [{}])[0].get('subtitle', '')}"),
+            'education': (f"{response_data.get('educations', [{}])[0].get('subtitle', '')} at "
+                          f"{response_data.get('educations', [{}])[0].get('title', '')}")
+        }
+        
+        # Append the dictionary to the list
+        profile_info_list.append(profile_info)
+
+    return profile_info_list
+
+# Function to populate DataFrame with LinkedIn information
+def get_LI_info(df):
+    links = df['Links'].tolist()
+    profile_info_list = scrape_linkedins(links)
+    
+    # Add new columns to the DataFrame
+    df['Full Name'] = ''
+    df['Headline'] = ''
+    df['Connections'] = ''
+    df['Country'] = ''
+    df['Address'] = ''
+    df['About'] = ''
+    df['Current Role'] = ''
+    df['Education'] = ''
+    
+    # Populate DataFrame with profile information
+    for i in range(len(profile_info_list)):
+        df.at[i, 'Full Name'] = profile_info_list[i]['full_name']
+        df.at[i, 'Headline'] = profile_info_list[i]['headline']
+        df.at[i, 'Connections'] = profile_info_list[i]['connections']
+        df.at[i, 'Country'] = profile_info_list[i]['country']
+        df.at[i, 'Address'] = profile_info_list[i]['address']
+        df.at[i, 'About'] = profile_info_list[i]['about']
+        df.at[i, 'Current Role'] = profile_info_list[i]['current_role']
+        df.at[i, 'Most Recent Education'] = profile_info_list[i]['education']
+    
+    return df
+        
+
+def get_scrape_data(csv_file, social_media):
+    df = pd.read_csv(csv_file.name)
+    if social_media == 'LinkedIN':
+        output_df = get_LI_info(df)
+    elif social_media == 'Instagram':
+        output_df = get_insta_info(df)
+        
+    file_name = './output.csv'
+    outpu_df.to_csv('./output.csv')
+    completion_status = "Done"
+    return completion_status, data_preview, gr.DownloadButton(label='Download AI Content', value=file_name, visible=True)
+    
+
+with gr.Blocks() as block:
+    gr.Markdown("""
+    # Social Media Scraper Dashboard
+    This dashboard is scrapes data from Linkedin and Instagram
+    """)
+
+    with gr.Column(visible=True):
+        gr.Markdown('''
+        # Scrape Content
+        Upload a spreadsheet with descriptions of website content
+        ''')
+        csv_file = gr.File(label='Input CSV File (must be CSV File)')
+        social_media = gr.Radio(choices=['LinkedIn', 'Instagram'], label='Which Social Media?', info = 'Which Social Media do you want to scrape from?')
+        con_gen_btn = gr.Button('Scrape')
+        status = gr.Textbox(label='Completion Status')
+        download_btn = gr.DownloadButton(label='Download Content', visible=False)
+
+    con_gen_btn.click(get_scarpe_data, inputs=[csv_file, social_media], outputs=[status, download_btn])
+    
+   
+block.queue(default_concurrency_limit=5)
+block.launch()