Skip to content
The Chat Archive
gpt-4-0314· OpenAI WildChat-4.8M (AI2)

ツールとして、InstagramのプロアカウントとFacebook APIやInstagram…

  1. User

    ツールとして、InstagramのプロアカウントとFacebook APIやInstagram グラフAPIとPython3を用いる事ができる状況において、①自分がInstagramで投稿したコンテンツを任意でアップロードせずとも、分析対象のコンテンツ画像をInstagramから自動でダウンロードして表示するようにしたうえで、当該コンテンツに対する"いいね"数やフォロー数に加えてそれぞれインプレッションからの割合のパーセント表示と、コメントしたメンバーのIDとアイコンを表示する機能を1ペインで表示し、②各コンテンツのインプレッションやエンゲージメントなど取得できうる限りのアナリティクス情報のデータを取得して横断的に分析できるように、StreamlitとStreamlitShareとブラウザを利用してインタラクティブなグラフやチャート等で2ペイン目で表示できるようにし、③表示するグラフデータの要素を変更する場合にはコードを改変せずともブラウザのUI上でクリックして要素をインタラクティブに選択変更できるようにし、④アプリケーションが開く際に毎回IDやAPI利用に関する情報入力が不要なように事前に必要な情報はコードに埋め込んであるコードを作成しようとしています。

    '''

    import streamlit as st import pandas as pd import requests import json import plotly.express as px from PIL import Image from io import BytesIO from collections import defaultdict

    環境変数または事前に入力された情報からアクセストークンとアカウントIDを設定

    access_token ="" account_id =""

    def get_instagram_data():

    base_url = f'https://graph.facebook.com/v11.0/{account_id}/media'
    params = {
        'fields': 'id,media_type,media_url,thumbnail_url,permalink,caption,timestamp,like_count,comments_count,comments{username,profile_picture_url,text},insights.metric(impressions,engagement)',
        'access_token': access_token
    }
    
    results = []
    
    while base_url:
        response = requests.get(base_url, params=params)
        data = json.loads(response.text)
    
        results.extend(data['data'])
    
        if 'paging' in data and 'next' in data['paging']:
            base_url = data['paging']['next']
        else:
            base_url = None
    
    for result in results:
        if not result.get('comments'):
            result['comments'] = {'data': []}
        if not "insights" in result:
            result["insights"] = [{"values": []}]
    
    grouped_results = defaultdict(list)
    
    for result in results:
        grouped_results[result['timestamp'].split("T")[0]].append(result)
    
    output = []
    for timestamp in grouped_results.keys():
        for idx, data in enumerate(grouped_results[timestamp], 1):
            data["meta_date_id"] = f'{timestamp.replace("-", "")}{idx}'
            output.append(data)
    
    df = pd.json_normalize(
        output,
        record_path=['comments', 'data'],
        meta=[
            'id', 'media_type', 'media_url', 'thumbnail_url',
            'permalink', 'caption', 'timestamp', 'like_count',
            'comments_count', 'insights', 'meta_date_id'
        ],
        meta_prefix='meta',
        errors='ignore'
    )
    df.rename(columns={'meta_timestamp': 'timestamp'}, inplace=True)
    df['timestamp'] = pd.to_datetime(df['timestamp']).dt.strftime('%Y%m%d')
    
    return df
    

    df = get_instagram_data()

    menu = ['Content', 'Analytics'] choice = st.sidebar.radio('Select Menu', menu)

    if choice == 'Content': selected_id = st.sidebar.selectbox('Select Post', df["meta_date_id"].unique()) selected_data = df[df["meta_date_id"] == selected_id].iloc[0] image_url = selected_data['meta_media_url'] if selected_data['meta_media_type'] == 'IMAGE' else selected_data['meta_thumbnail_url']

    if pd.notna(image_url):
        image_response = requests.get(image_url)
        image = Image.open(BytesIO(image_response.content))
        st.image(image, use_column_width=True)
    else:
        st.write('Image not found')
    
    meta_insights = selected_data.get('meta_insights')
    try:
        if meta_insights and len(meta_insights) > 0 and len(meta_insights[0]["values"]) > 0:
            impressions_value = meta_insights[0]["values"][0].get("value", 0)
            like_percentage = (selected_data['meta_like_count'] / impressions_value) * 100
        else:
            like_percentage = 0
    except KeyError:
        like_percentage = 0
    
    st.write(f'Likes: {selected_data["meta_like_count"]} ({like_percentage:.2f}%)')
    st.write(f'Comments: {selected_data["meta_comments_count"]}')
    
    comments_df = df[df["meta_date_id"] == selected_id]
    st.write(comments_df[['username', 'text']])
    

    elif choice == 'Analytics': categories = ['Impressions', 'Engagement'] selected_category = st.selectbox('Select metric', categories)

    if selected_category == 'Impressions':
        pass
    elif selected_category == 'Engagement':
        pass
    

    '''

    上記コードを実行すると下記のエラーが発生します。行頭にPython用のインデントを付与した修正コードを表示してください。

    ‘’‘ KeyError Traceback (most recent call last) File ~/.var/app/org.jupyter.JupyterLab/config/jupyterlab-desktop/jlab_server/lib/python3.8/site-packages/pandas/core/indexes/base.py:3802, in Index.get_loc(self, key, method, tolerance) 3801 try: -> 3802 return self._engine.get_loc(casted_key) 3803 except KeyError as err:

    File ~/.var/app/org.jupyter.JupyterLab/config/jupyterlab-desktop/jlab_server/lib/python3.8/site-packages/pandas/_libs/index.pyx:138, in pandas._libs.index.IndexEngine.get_loc()

    File ~/.var/app/org.jupyter.JupyterLab/config/jupyterlab-desktop/jlab_server/lib/python3.8/site-packages/pandas/_libs/index.pyx:165, in pandas._libs.index.IndexEngine.get_loc()

    File pandas/_libs/hashtable_class_helper.pxi:5745, in pandas._libs.hashtable.PyObjectHashTable.get_item()

    File pandas/_libs/hashtable_class_helper.pxi:5753, in pandas._libs.hashtable.PyObjectHashTable.get_item()

    KeyError: ‘timestamp’

    The above exception was the direct cause of the following exception:

    KeyError Traceback (most recent call last) Cell In[50], line 68 64 df[‘timestamp’] = pd.to_datetime(df[‘timestamp’]).dt.strftime(’%Y%m%d’) 66 return df —> 68 df = get_instagram_data() 70 menu = [‘Content’, ‘Analytics’] 71 choice = st.sidebar.radio(‘Select Menu’, menu)

    Cell In[50], line 64, in get_instagram_data() 52 df = pd.json_normalize( 53 output, 54 record_path=[‘comments’, ‘data’], (…) 61 errors=‘ignore’ 62 ) 63 df.rename(columns={‘meta_timestamp’: ‘timestamp’}, inplace=True) —> 64 df[‘timestamp’] = pd.to_datetime(df[‘timestamp’]).dt.strftime(‘%Y%m%d’) 66 return df

    File ~/.var/app/org.jupyter.JupyterLab/config/jupyterlab-desktop/jlab_server/lib/python3.8/site-packages/pandas/core/frame.py:3807, in DataFrame.getitem(self, key) 3805 if self.columns.nlevels > 1: 3806 return self._getitem_multilevel(key) -> 3807 indexer = self.columns.get_loc(key) 3808 if is_integer(indexer): 3809 indexer = [indexer]

    File ~/.var/app/org.jupyter.JupyterLab/config/jupyterlab-desktop/jlab_server/lib/python3.8/site-packages/pandas/core/indexes/base.py:3804, in Index.get_loc(self, key, method, tolerance) 3802 return self._engine.get_loc(casted_key) 3803 except KeyError as err: -> 3804 raise KeyError(key) from err 3805 except TypeError: 3806 # If we have a listlike key, _check_indexing_error will raise 3807 # InvalidIndexError. Otherwise we fall through and re-raise 3808 # the TypeError. 3809 self._check_indexing_error(key)

    KeyError: ‘timestamp’ ‘’’

  2. Assistant

    以下の修正後のコードをお試しください。

    import streamlit as st
    import pandas as pd
    import requests
    import json
    import plotly.express as px
    from PIL import Image
    from io import BytesIO
    from collections import defaultdict
    
    # 環境変数または事前に入力された情報からアクセストークンとアカウントIDを設定
    access_token =""
    account_id =""
    
    def get_instagram_data():
    
        base_url = f'https://graph.facebook.com/v11.0/{account_id}/media'
        params = {
            'fields': 'id,media_type,media_url,thumbnail_url,permalink,caption,timestamp,like_count,comments_count,comments{username,profile_picture_url,text},insights.metric(impressions,engagement)',
            'access_token': access_token
        }
    
        results = []
    
        while base_url:
            response = requests.get(base_url, params=params)
            data = json.loads(response.text)
    
            results.extend(data['data'])
    
            if 'paging' in data and 'next' in data['paging']:
                base_url = data['paging']['next']
            else:
                base_url = None
    
        for result in results:
            if not result.get('comments'):
                result['comments'] = {'data': []}
            if not "insights" in result:
                result["insights"] = [{"values": []}]
    
        grouped_results = defaultdict(list)
    
        for result in results:
            grouped_results[result['timestamp'].split("T")[0]].append(result)
    
        output = []
        for timestamp in grouped_results.keys():
            for idx, data in enumerate(grouped_results[timestamp], 1):
                data["meta_date_id"] = f'{timestamp.replace("-", "")}{idx}'
                output.append(data)
    
        df = pd.json_normalize(
            output,
            record_path=['comments', 'data'],
            meta=[
                'id', 'media_type', 'media_url', 'thumbnail_url',
                'permalink', 'caption', 'timestamp', 'like_count',
                'comments_count', 'insights', 'meta_date_id'
            ],
            meta_prefix='meta',
            errors='ignore'
        )
        df.rename(columns={'meta_timestamp': 'timestamp'}, inplace=True)
        if 'timestamp' in df.columns:
            df['timestamp'] = pd.to_datetime(df['timestamp']).dt.strftime('%Y%m%d')
    
        return df
    
    df = get_instagram_data()
    
    menu = ['Content', 'Analytics']
    choice = st.sidebar.radio('Select Menu', menu)
    
    if choice == 'Content':
        selected_id = st.sidebar.selectbox('Select Post', df["meta_date_id"].unique())
        selected_data = df[df["meta_date_id"] == selected_id].iloc[0]
        image_url = selected_data['meta_media_url'] if selected_data['meta_media_type'] == 'IMAGE' else selected_data['meta_thumbnail_url']
    
        if pd.notna(image_url):
            image_response = requests.get(image_url)
            image = Image.open(BytesIO(image_response.content))
            st.image(image, use_column_width=True)
        else:
            st.write('Image not found')
    
        meta_insights = selected_data.get('meta_insights')
        try:
            if meta_insights and len(meta_insights) > 0 and len(meta_insights[0]["values"]) > 0:
                impressions_value = meta_insights[0]["values"][0].get("value", 0)
                like_percentage = (selected_data['meta_like_count'] / impressions_value) * 100
            else:
                like_percentage = 0
        except KeyError:
            like_percentage = 0
    
        st.write(f'Likes: {selected_data["meta_like_count"]} ({like_percentage:.2f}%)')
        st.write(f'Comments: {selected_data["meta_comments_count"]}')
    
        comments_df = df[df["meta_date_id"] == selected_id]
        st.write(comments_df[['username', 'text']])
    
    elif choice == 'Analytics':
        categories = ['Impressions', 'Engagement']
        selected_category = st.selectbox('Select metric', categories)
    
        if selected_category == 'Impressions':
            pass
        elif selected_category == 'Engagement':
            pass
    
  3. User

    上記コードにおいて、Pythonで必要なインデント表示がありません。行頭にインデントを付与して再掲してください。

  4. Assistant

    ご指摘いただき、ありがとうございます。Python用のインデントを適切に設定したコードを以下に示します。

    import streamlit as st
    import pandas as pd
    import requests
    import json
    import plotly.express as px
    from PIL import Image
    from io import BytesIO
    from collections import defaultdict
    
    # 環境変数または事前に入力された情報からアクセストークンとアカウントIDを設定
    access_token =""
    account_id =""
    
    def get_instagram_data():
    
        base_url = f'https://graph.facebook.com/v11.0/{account_id}/media'
        params = {
            'fields': 'id,media_type,media_url,thumbnail_url,permalink,caption,timestamp,like_count,comments_count,comments{username,profile_picture_url,text},insights.metric(impressions,engagement)',
            'access_token': access_token
        }
    
        results = []
    
        while base_url:
            response = requests.get(base_url, params=params)
            data = json.loads(response.text)
    
            results.extend(data['data'])
    
            if 'paging' in data and 'next' in data['paging']:
                base_url = data['paging']['next']
            else:
                base_url = None
    
        for result in results:
            if not result.get('comments'):
                result['comments'] = {'data': []}
            if not "insights" in result:
                result["insights"] = [{"values": []}]
    
        grouped_results = defaultdict(list)
    
        for result in results:
            grouped_results[result['timestamp'].split("T")[0]].append(result)
    
        output = []
        for timestamp in grouped_results.keys():
            for idx, data in enumerate(grouped_results[timestamp], 1):
                data["meta_date_id"] = f'{timestamp.replace("-", "")}{idx}'
                output.append(data)
    
        df = pd.json_normalize(
            output,
            record_path=['comments', 'data'],
            meta=[
                'id', 'media_type', 'media_url', 'thumbnail_url',
                'permalink', 'caption', 'timestamp', 'like_count',
                'comments_count', 'insights', 'meta_date_id'
            ],
            meta_prefix='meta',
            errors='ignore'
        )
        df.rename(columns={'meta_timestamp': 'timestamp'}, inplace=True)
        if 'timestamp' in df.columns:
            df['timestamp'] = pd.to_datetime(df['timestamp']).dt.strftime('%Y%m%d')
    
        return df
    
    df = get_instagram_data()
    
    menu = ['Content', 'Analytics']
    choice = st.sidebar.radio('Select Menu', menu)
    
    if choice == 'Content':
        selected_id = st.sidebar.selectbox('Select Post', df["meta_date_id"].unique())
        selected_data = df[df["meta_date_id"] == selected_id].iloc[0]
        image_url = selected_data['meta_media_url'] if selected_data['meta_media_type'] == 'IMAGE' else selected_data['meta_thumbnail_url']
    
        if pd.notna(image_url):
            image_response = requests.get(image_url)
            image = Image.open(BytesIO(image_response.content))
            st.image(image, use_column_width=True)
        else:
            st.write('Image not found')
    
        meta_insights = selected_data.get('meta_insights')
        try:
            if meta_insights and len(meta_insights) > 0 and len(meta_insights[0]["values"]) > 0:
                impressions_value = meta_insights[0]["values"][0].get("value", 0)
                like_percentage = (selected_data['meta_like_count'] / impressions_value) * 100
            else:
                like_percentage = 0
        except KeyError:
            like_percentage = 0
    
        st.write(f'Likes: {selected_data["meta_like_count"]} ({like_percentage:.2f}%)')
        st.write(f'Comments: {selected_data["meta_comments_count"]}')
    
        comments_df = df[df["meta_date_id"] == selected_id]
        st.write(comments_df[['username', 'text']])
    
    elif choice == 'Analytics':
        categories = ['Impressions', 'Engagement']
        selected_category = st.selectbox('Select metric', categories)
    
        if selected_category == 'Impressions':
            pass
        elif selected_category == 'Engagement':
            pass