langchain/docs/modules/indexes/document_loaders/examples/twitter.ipynb

115 lines
16 KiB
Plaintext
Raw Normal View History

{
"cells": [
{
"cell_type": "markdown",
"id": "66a7777e",
"metadata": {},
"source": [
"# Twitter\n",
"\n",
"This loader fetches the text from the Tweets of a list of Twitter users, using the `tweepy` Python package.\n",
"You must initialize the loader with your Twitter API token, and you need to pass in the Twitter username you want to extract."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9ec8a3b3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TwitterTweetLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "43128d8d",
"metadata": {},
"outputs": [],
"source": [
"#!pip install tweepy"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "35d6809a",
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"loader = TwitterTweetLoader.from_bearer_token(\n",
" oauth2_bearer_token=\"YOUR BEARER TOKEN\",\n",
" twitter_users=['elonmusk'],\n",
" number_tweets=50, # Default value is 100\n",
")\n",
"\n",
"# Or load from access token and consumer keys\n",
"# loader = TwitterTweetLoader.from_secrets(\n",
"# access_token='YOUR ACCESS TOKEN',\n",
"# access_token_secret='YOUR ACCESS TOKEN SECRET',\n",
"# consumer_key='YOUR CONSUMER KEY',\n",
"# consumer_secret='YOUR CONSUMER SECRET',\n",
"# twitter_users=['elonmusk'],\n",
"# number_tweets=50,\n",
"# )"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "05fe33b9",
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='@MrAndyNgo @REI One store after another shutting down', metadata={'created_at': 'Tue Apr 18 03:45:50 +0000 2023', 'user_info': {'id': 44196397, 'id_str': '44196397', 'name': 'Elon Musk', 'screen_name': 'elonmusk', 'location': 'A Shortfall of Gravitas', 'profile_location': None, 'description': 'nothing', 'url': None, 'entities': {'description': {'urls': []}}, 'protected': False, 'followers_count': 135528327, 'friends_count': 220, 'listed_count': 120478, 'created_at': 'Tue Jun 02 20:12:29 +0000 2009', 'favourites_count': 21285, 'utc_offset': None, 'time_zone': None, 'geo_enabled': False, 'verified': False, 'statuses_count': 24795, 'lang': None, 'status': {'created_at': 'Tue Apr 18 03:45:50 +0000 2023', 'id': 1648170947541704705, 'id_str': '1648170947541704705', 'text': '@MrAndyNgo @REI One store after another shutting down', 'truncated': False, 'entities': {'hashtags': [], 'symbols': [], 'user_mentions': [{'screen_name': 'MrAndyNgo', 'name': 'Andy Ngô 🏳️\\u200d🌈', 'id': 2835451658, 'id_str': '2835451658', 'indices': [0, 10]}, {'screen_name': 'REI', 'name': 'REI', 'id': 16583846, 'id_str': '16583846', 'indices': [11, 15]}], 'urls': []}, 'source': '<a href=\"http://twitter.com/download/iphone\" rel=\"nofollow\">Twitter for iPhone</a>', 'in_reply_to_status_id': 1648134341678051328, 'in_reply_to_status_id_str': '1648134341678051328', 'in_reply_to_user_id': 2835451658, 'in_reply_to_user_id_str': '2835451658', 'in_reply_to_screen_name': 'MrAndyNgo', 'geo': None, 'coordinates': None, 'place': None, 'contributors': None, 'is_quote_status': False, 'retweet_count': 118, 'favorite_count': 1286, 'favorited': False, 'retweeted': False, 'lang': 'en'}, 'contributors_enabled': False, 'is_translator': False, 'is_translation_enabled': False, 'profile_background_color': 'C0DEED', 'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_tile': False, 'profile_image_url': 'http://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_image_url_https': 'https://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_banner_url': 'https://pbs.twimg.com/profile_banners/44196397/1576183471', 'profile_link_color': '0084B4', 'profile_sidebar_border_color': 'C0DEED', 'profile_sidebar_fill_color': 'DDEEF6', 'profile_text_color': '333333', 'profile_use_background_image': True, 'has_extended_profile': True, 'default_profile': False, 'default_profile_image': False, 'following': None, 'follow_request_sent': None, 'notifications': None, 'translator_type': 'none', 'withheld_in_countries': []}}),\n",
" Document(page_content='@KanekoaTheGreat @joshrogin @glennbeck Large ships are fundamentally vulnerable to ballistic (hypersonic) missiles', metadata={'created_at': 'Tue Apr 18 03:43:25 +0000 2023', 'user_info': {'id': 44196397, 'id_str': '44196397', 'name': 'Elon Musk', 'screen_name': 'elonmusk', 'location': 'A Shortfall of Gravitas', 'profile_location': None, 'description': 'nothing', 'url': None, 'entities': {'description': {'urls': []}}, 'protected': False, 'followers_count': 135528327, 'friends_count': 220, 'listed_count': 120478, 'created_at': 'Tue Jun 02 20:12:29 +0000 2009', 'favourites_count': 21285, 'utc_offset': None, 'time_zone': None, 'geo_enabled': False, 'verified': False, 'statuses_count': 24795, 'lang': None, 'status': {'created_at': 'Tue Apr 18 03:45:50 +0000 2023', 'id': 1648170947541704705, 'id_str': '1648170947541704705', 'text': '@MrAndyNgo @REI One store after another shutting down', 'truncated': False, 'entities': {'hashtags': [], 'symbols': [], 'user_mentions': [{'screen_name': 'MrAndyNgo', 'name': 'Andy Ngô 🏳️\\u200d🌈', 'id': 2835451658, 'id_str': '2835451658', 'indices': [0, 10]}, {'screen_name': 'REI', 'name': 'REI', 'id': 16583846, 'id_str': '16583846', 'indices': [11, 15]}], 'urls': []}, 'source': '<a href=\"http://twitter.com/download/iphone\" rel=\"nofollow\">Twitter for iPhone</a>', 'in_reply_to_status_id': 1648134341678051328, 'in_reply_to_status_id_str': '1648134341678051328', 'in_reply_to_user_id': 2835451658, 'in_reply_to_user_id_str': '2835451658', 'in_reply_to_screen_name': 'MrAndyNgo', 'geo': None, 'coordinates': None, 'place': None, 'contributors': None, 'is_quote_status': False, 'retweet_count': 118, 'favorite_count': 1286, 'favorited': False, 'retweeted': False, 'lang': 'en'}, 'contributors_enabled': False, 'is_translator': False, 'is_translation_enabled': False, 'profile_background_color': 'C0DEED', 'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_tile': False, 'profile_image_url': 'http://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_image_url_https': 'https://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_banner_url': 'https://pbs.twimg.com/profile_banners/44196397/1576183471', 'profile_link_color': '0084B4', 'profile_sidebar_border_color': 'C0DEED', 'profile_sidebar_fill_color': 'DDEEF6', 'profile_text_color': '333333', 'profile_use_background_image': True, 'has_extended_profile': True, 'default_profile': False, 'default_profile_image': False, 'following': None, 'follow_request_sent': None, 'notifications': None, 'translator_type': 'none', 'withheld_in_countries': []}}),\n",
" Document(page_content='@KanekoaTheGreat The Golden Rule', metadata={'created_at': 'Tue Apr 18 03:37:17 +0000 2023', 'user_info': {'id': 44196397, 'id_str': '44196397', 'name': 'Elon Musk', 'screen_name': 'elonmusk', 'location': 'A Shortfall of Gravitas', 'profile_location': None, 'description': 'nothing', 'url': None, 'entities': {'description': {'urls': []}}, 'protected': False, 'followers_count': 135528327, 'friends_count': 220, 'listed_count': 120478, 'created_at': 'Tue Jun 02 20:12:29 +0000 2009', 'favourites_count': 21285, 'utc_offset': None, 'time_zone': None, 'geo_enabled': False, 'verified': False, 'statuses_count': 24795, 'lang': None, 'status': {'created_at': 'Tue Apr 18 03:45:50 +0000 2023', 'id': 1648170947541704705, 'id_str': '1648170947541704705', 'text': '@MrAndyNgo @REI One store after another shutting down', 'truncated': False, 'entities': {'hashtags': [], 'symbols': [], 'user_mentions': [{'screen_name': 'MrAndyNgo', 'name': 'Andy Ngô 🏳️\\u200d🌈', 'id': 2835451658, 'id_str': '2835451658', 'indices': [0, 10]}, {'screen_name': 'REI', 'name': 'REI', 'id': 16583846, 'id_str': '16583846', 'indices': [11, 15]}], 'urls': []}, 'source': '<a href=\"http://twitter.com/download/iphone\" rel=\"nofollow\">Twitter for iPhone</a>', 'in_reply_to_status_id': 1648134341678051328, 'in_reply_to_status_id_str': '1648134341678051328', 'in_reply_to_user_id': 2835451658, 'in_reply_to_user_id_str': '2835451658', 'in_reply_to_screen_name': 'MrAndyNgo', 'geo': None, 'coordinates': None, 'place': None, 'contributors': None, 'is_quote_status': False, 'retweet_count': 118, 'favorite_count': 1286, 'favorited': False, 'retweeted': False, 'lang': 'en'}, 'contributors_enabled': False, 'is_translator': False, 'is_translation_enabled': False, 'profile_background_color': 'C0DEED', 'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_tile': False, 'profile_image_url': 'http://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_image_url_https': 'https://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_banner_url': 'https://pbs.twimg.com/profile_banners/44196397/1576183471', 'profile_link_color': '0084B4', 'profile_sidebar_border_color': 'C0DEED', 'profile_sidebar_fill_color': 'DDEEF6', 'profile_text_color': '333333', 'profile_use_background_image': True, 'has_extended_profile': True, 'default_profile': False, 'default_profile_image': False, 'following': None, 'follow_request_sent': None, 'notifications': None, 'translator_type': 'none', 'withheld_in_countries': []}}),\n",
" Document(page_content='@KanekoaTheGreat 🧐', metadata={'created_at': 'Tue Apr 18 03:35:48 +0000 2023', 'user_info': {'id': 44196397, 'id_str': '44196397', 'name': 'Elon Musk', 'screen_name': 'elonmusk', 'location': 'A Shortfall of Gravitas', 'profile_location': None, 'description': 'nothing', 'url': None, 'entities': {'description': {'urls': []}}, 'protected': False, 'followers_count': 135528327, 'friends_count': 220, 'listed_count': 120478, 'created_at': 'Tue Jun 02 20:12:29 +0000 2009', 'favourites_count': 21285, 'utc_offset': None, 'time_zone': None, 'geo_enabled': False, 'verified': False, 'statuses_count': 24795, 'lang': None, 'status': {'created_at': 'Tue Apr 18 03:45:50 +0000 2023', 'id': 1648170947541704705, 'id_str': '1648170947541704705', 'text': '@MrAndyNgo @REI One store after another shutting down', 'truncated': False, 'entities': {'hashtags': [], 'symbols': [], 'user_mentions': [{'screen_name': 'MrAndyNgo', 'name': 'Andy Ngô 🏳️\\u200d🌈', 'id': 2835451658, 'id_str': '2835451658', 'indices': [0, 10]}, {'screen_name': 'REI', 'name': 'REI', 'id': 16583846, 'id_str': '16583846', 'indices': [11, 15]}], 'urls': []}, 'source': '<a href=\"http://twitter.com/download/iphone\" rel=\"nofollow\">Twitter for iPhone</a>', 'in_reply_to_status_id': 1648134341678051328, 'in_reply_to_status_id_str': '1648134341678051328', 'in_reply_to_user_id': 2835451658, 'in_reply_to_user_id_str': '2835451658', 'in_reply_to_screen_name': 'MrAndyNgo', 'geo': None, 'coordinates': None, 'place': None, 'contributors': None, 'is_quote_status': False, 'retweet_count': 118, 'favorite_count': 1286, 'favorited': False, 'retweeted': False, 'lang': 'en'}, 'contributors_enabled': False, 'is_translator': False, 'is_translation_enabled': False, 'profile_background_color': 'C0DEED', 'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_tile': False, 'profile_image_url': 'http://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_image_url_https': 'https://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_banner_url': 'https://pbs.twimg.com/profile_banners/44196397/1576183471', 'profile_link_color': '0084B4', 'profile_sidebar_border_color': 'C0DEED', 'profile_sidebar_fill_color': 'DDEEF6', 'profile_text_color': '333333', 'profile_use_background_image': True, 'has_extended_profile': True, 'default_profile': False, 'default_profile_image': False, 'following': None, 'follow_request_sent': None, 'notifications': None, 'translator_type': 'none', 'withheld_in_countries': []}}),\n",
" Document(page_content='@TRHLofficial Whats he talking about and why is it sponsored by Eriks son?', metadata={'created_at': 'Tue Apr 18 03:32:17 +0000 2023', 'user_info': {'id': 44196397, 'id_str': '44196397', 'name': 'Elon Musk', 'screen_name': 'elonmusk', 'location': 'A Shortfall of Gravitas', 'profile_location': None, 'description': 'nothing', 'url': None, 'entities': {'description': {'urls': []}}, 'protected': False, 'followers_count': 135528327, 'friends_count': 220, 'listed_count': 120478, 'created_at': 'Tue Jun 02 20:12:29 +0000 2009', 'favourites_count': 21285, 'utc_offset': None, 'time_zone': None, 'geo_enabled': False, 'verified': False, 'statuses_count': 24795, 'lang': None, 'status': {'created_at': 'Tue Apr 18 03:45:50 +0000 2023', 'id': 1648170947541704705, 'id_str': '1648170947541704705', 'text': '@MrAndyNgo @REI One store after another shutting down', 'truncated': False, 'entities': {'hashtags': [], 'symbols': [], 'user_mentions': [{'screen_name': 'MrAndyNgo', 'name': 'Andy Ngô 🏳️\\u200d🌈', 'id': 2835451658, 'id_str': '2835451658', 'indices': [0, 10]}, {'screen_name': 'REI', 'name': 'REI', 'id': 16583846, 'id_str': '16583846', 'indices': [11, 15]}], 'urls': []}, 'source': '<a href=\"http://twitter.com/download/iphone\" rel=\"nofollow\">Twitter for iPhone</a>', 'in_reply_to_status_id': 1648134341678051328, 'in_reply_to_status_id_str': '1648134341678051328', 'in_reply_to_user_id': 2835451658, 'in_reply_to_user_id_str': '2835451658', 'in_reply_to_screen_name': 'MrAndyNgo', 'geo': None, 'coordinates': None, 'place': None, 'contributors': None, 'is_quote_status': False, 'retweet_count': 118, 'favorite_count': 1286, 'favorited': False, 'retweeted': False, 'lang': 'en'}, 'contributors_enabled': False, 'is_translator': False, 'is_translation_enabled': False, 'profile_background_color': 'C0DEED', 'profile_background_image_url': 'http://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_image_url_https': 'https://abs.twimg.com/images/themes/theme1/bg.png', 'profile_background_tile': False, 'profile_image_url': 'http://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_image_url_https': 'https://pbs.twimg.com/profile_images/1590968738358079488/IY9Gx6Ok_normal.jpg', 'profile_banner_url': 'https://pbs.twimg.com/profile_banners/44196397/1576183471', 'profile_link_color': '0084B4', 'profile_sidebar_border_color': 'C0DEED', 'profile_sidebar_fill_color': 'DDEEF6', 'profile_text_color': '333333', 'profile_use_background_image': True, 'has_extended_profile': True, 'default_profile': False, 'default_profile_image': False, 'following': None, 'follow_request_sent': None, 'notifications': None, 'translator_type': 'none', 'withheld_in_countries': []}})]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"documents = loader.load()\n",
"documents[:5]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}