{"id":1624,"date":"2023-04-06T22:17:18","date_gmt":"2023-04-06T13:17:18","guid":{"rendered":"https:\/\/fukugyouhistory.tokyo\/?p=1624"},"modified":"2023-04-07T00:28:26","modified_gmt":"2023-04-06T15:28:26","slug":"python%e3%80%80stweet%ef%bc%8bwordcloud%e3%81%a7twitter%e3%81%ae%e3%83%88%e3%83%ac%e3%83%b3%e3%83%89%e3%82%92%e5%8f%af%e8%a6%96%e5%8c%96%e3%81%97%e3%81%a6%e3%81%bf%e3%81%9f","status":"publish","type":"post","link":"https:\/\/fukugyouhistory.tokyo\/?p=1624","title":{"rendered":"Python\u3000stweet\uff0bWordCloud\u3000Twitter\u306e\u30c8\u30ec\u30f3\u30c9\u3092\u53ef\u8996\u5316\u3057\u3066\u307f\u305f"},"content":{"rendered":"\n

Twitter\u306e\u6295\u7a3f\u5185\u5bb9\u3092\u30b5\u30fc\u30c9API\u3067\u53d6\u5f97\u3059\u308b\u30e9\u30a4\u30d6\u30e9\u30eastweet<\/a>\u3068\u3001\u6587\u4e2d\u306e\u51fa\u73fe\u983b\u5ea6\u306e\u9ad8\u3044\u5358\u8a9e\u3092\u62bd\u51fa\u3057\u3066\u53ef\u8996\u5316\u3059\u308b\u30c4\u30fc\u30ebWordCloud<\/a>\u3092\u7528\u3044\u3066\u3001Twitter\u306e\u30c8\u30ec\u30f3\u30c9\u3092\u53ef\u8996\u5316\u3057\u3066\u307f\u307e\u3057\u305f\u3002<\/p>\n\n\n\n

\u691c\u7d22\u30ad\u30fc\u30ef\u30fc\u30c9\u3092\u5909\u66f4\u3059\u308b\u3053\u3068\u3067\u3001\u81ea\u5206\u306e\u53d6\u5f97\u3057\u305f\u3044\u60c5\u5831\u3092\u53ef\u8996\u5316\u3057\u3066\u6349\u3048\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u306e\u3067\u3001\u6709\u7528\u304b\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n\n\n\n\n\n\n\n

<\/p>\n\n\n\n

stweet\u3092\u7528\u3044\u3066\u6295\u7a3f\u306e\u60c5\u5831\u3092\u96c6\u3081\u308b<\/h2>\n\n\n\n

\u6700\u521d\u306bstweet\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002
\u5408\u308f\u305b\u3066\u3001stweet\u3067\u306f\u65e5\u4ed8\u60c5\u5831\u3092arrow\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u7528\u3044\u3066\u6307\u5b9a\u3057\u307e\u3059\u306e\u3067\u3001\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n\n\n\n

!pip install stweet\n!pip install arrow<\/code><\/pre>\n\n\n\n
\u3053\u3053\u3067\u306f\u3001\u6700\u8fd1\u8a71\u984c\u306e\u300cchatGPT\u300d\u306e\u60c5\u5831\u3092\u53d6\u5f97\u3057\u3066\u307f\u307e\u3059\u3002
\u6642\u9593\u5358\u4f4d\u3067\u3082\u6307\u5b9a\u3057\u305f\u306e\u3067\u3059\u304c\u3046\u307e\u304f\u52d5\u304b\u306a\u304b\u3063\u305f\u306e\u3067\u3001\u65e5\u4ed8\u6307\u5b9a\u306f1\u65e5\u5358\u4f4d\u3067\u3057\u304b\u3067\u304d\u306a\u3044\u3088\u3046\u3067\u3059\u3002<\/p>\n\n\n\n
\u5f8c\u65e5\u3001\u8ffd\u52a0\u3002stweet\u306e\u30b5\u30a4\u30c8\u60c5\u5831\u306b\u3088\u308b\u3068\u30012023\u5e74\u4ee5\u964d\u306e\u6295\u7a3f\u306f\u6642\u9593\u6307\u5b9a\u304c\u5f3e\u304b\u308c\u308b\u3088\u3046\u3067\u3059\u3002<\/mark><\/p>\n\n\n\n
\n
Twitter in 2023 block in API putting time range in timestamp \u2013 only format YYYY-MM-DD is acceptable. In arrow you can only put time without hours.<\/p>\n<\/blockquote>\n\n\n\n
\u53d6\u5f97\u3057\u305f\u60c5\u5831\u306fjson\u5f62\u5f0f\u3067\u51fa\u529b\u3055\u308c\u308b\u306e\u3067\u3059\u304c\u3001\u4e0a\u66f8\u304d\u3067\u306a\u304f\u8ffd\u8a18\u3055\u308c\u3066\u3044\u304d\u307e\u3059\u306e\u3067\u3001
\u6700\u521d\u306b\u904e\u53bb\u30d5\u30a1\u30a4\u30eb\u306e\u524a\u9664\u3092\u5b9f\u65bd\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
# Output\u304c\u8ffd\u8a18\u65b9\u5f0f\u306e\u305f\u3081\u3001\u53e4\u3044\u30c7\u30fc\u30bf\u3092\u524a\u9664\n# windows\n!del output_raw_*\n# linux\n#!rm output_raw_*<\/code><\/pre>\n\n\n\n
\u5b9f\u969b\u306e\u53d6\u5f97\u3059\u308b\u30b3\u30fc\u30c9\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3002\u8a2d\u5b9a\u306a\u3069\u306f\u3001\u30b3\u30e1\u30f3\u30c8\u3067\u8a18\u8f09\u3057\u3066\u304a\u304d\u307e\u3059\u3002
\u8a73\u3057\u304f\u306f\u3001stweet<\/a>\u306e\u60c5\u5831\u3092\u53c2\u8003\u306b\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n
import stweet as st\nimport arrow\n\n# \u691c\u7d22\u30ef\u30fc\u30c9\nkey_words=\"chatGPT \u30cb\u30e5\u30fc\u30b9\"\n\n# and\u691c\u7d22\u306e\u5834\u5408\nall_words=key_words\n# or\u691c\u7d22\u306e\u5834\u5408\n#any_words=key_words\n\n# \u691c\u7d22\u7bc4\u56f2\u306e\u6642\u9593\nsince = arrow.get(\"2023-04-04\")\nuntil = since.shift(days=+1)\n\n# \u691c\u7d22\u7bc4\u56f2\u306e\u8a00\u8a9e\nlanguage=st.Language.JAPANESE\n\n# \u30aa\u30ea\u30b8\u30ca\u30eb\u30c4\u30a4\u30fc\u30c8\u306e\u307f\nreplies_filter=\"ONLY_ORIGINAL\"\n# \u30ea\u30d7\u30e9\u30a4\u306e\u307f\n#replies_filter=\"ONLY_REPLIES\"\n\n# stweet\u306e\u5b9f\u884c\nsearch_tweets_task = st.SearchTweetsTask(all_words=all_words, since=since, until=until, language=language, replies_filter=replies_filter)\noutput_jl_tweets = st.JsonLineFileRawOutput('output_raw_search_tweets.jl')\noutput_jl_users = st.JsonLineFileRawOutput('output_raw_search_users.jl')\n\n# \u51e6\u7406\u4e2d\u306e\u51fa\u529b\n# \u3059\u3079\u3066\u51fa\u529b\n#output_print = st.PrintRawOutput()\n# 100\u51e6\u7406\u3054\u3068\u306b\u51fa\u529b\n#output_print = st.PrintEveryNRawOutput(100)\n# \u30e1\u30e2\u30ea\u306b\u6d41\u3059\noutput_print = st.CollectorRawOutput()\n\n# \u53ce\u96c6\u51e6\u7406\u306e\u5b9f\u884c\nst.TweetSearchRunner(search_tweets_task=search_tweets_task, \n                     tweet_raw_data_outputs=[output_print, output_jl_tweets], \n                     user_raw_data_outputs=[output_print, output_jl_users]).run()<\/code><\/pre>\n\n\n\n
\u5b9f\u884c\u7d50\u679c\u3067\u3001\u4f55\u4ef6\u306e\u6295\u7a3f\u30c7\u30fc\u30bf\u304c\u53d6\u5f97\u3067\u304d\u305f\u304b\u8868\u793a\u3055\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\u5b9f\u884c\u3057\u3066\u51fa\u529b\u3055\u308c\u305fjson\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3093\u3067\u3001\u7d50\u679c\u3092\u898b\u3066\u307f\u307e\u3059\u3002<\/p>\n\n\n\n
import pandas as pd\n\n# \u7d50\u679c\u306e\u30c4\u30a4\u30fc\u30c8\u30d5\u30a1\u30a4\u30eb\u306e\u8aad\u307f\u8fbc\u307f\njson_open = pd.read_json(\"output_raw_search_tweets.jl\", orient='records', lines=True)\n\nfor json_tmp in json_open[\"raw_value\"]:\n    print(json_tmp[\"full_text\"])\n    \n    # WordCloud\u7528\u306bstr\u5f62\u5f0f\u3067\u51fa\u529b\u7d50\u679c\u3092\u4ee3\u5165\u3057\u3066\u304a\u304f\n    text = text + json_tmp[\"full_text\"] + \"\\n\"<\/code><\/pre>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\n\n\n\n
\u53c2\u8003\u307e\u3067\u306b\u3001\u7279\u5b9a\u306e\u30e6\u30fc\u30b6\u30fc\u540d\u3001\u7279\u5b9a\u306e\u30c4\u30a4\u30fc\u30c8ID\u306e\u6295\u7a3f\u3092\u53d6\u5f97\u3059\u308b\u65b9\u6cd5\u3082\u3042\u308a\u307e\u3059\u3002
\u65e5\u4ed8\u6307\u5b9a\u304c\u3067\u304d\u307e\u305b\u3093\u306e\u3067\u3001\u30e6\u30fc\u30b6\u30fc\u540d\u306b\u3088\u3063\u3066\u306f\u5927\u91cf\u306e\u30c7\u30fc\u30bf\u3092\u53d6\u5f97\u3059\u308b\u3053\u3068\u306b\u306a\u308b\u306e\u3067\u3001\u6ce8\u610f\u304c\u5fc5\u8981\u3067\u3059\u3002<\/p>\n\n\n\n
import stweet as st\nimport arrow\n\n# \u7279\u5b9a\u306e\u30e6\u30fc\u30b6\u30fc\u540d\u306e\u6295\u7a3f\u3092\u53d6\u5f97\u3059\u308b\u5834\u5408\nuser_task = st.GetUsersTask(['iga_swiatek'])\noutput_json = st.JsonLineFileRawOutput('output_raw_user.jl')\noutput_print = st.CollectorRawOutput()\nst.GetUsersRunner(get_user_task=user_task, raw_data_outputs=[output_print, output_json]).run()<\/code><\/pre>\n\n\n\n
import stweet as st\nimport arrow\n\n# \u7279\u5b9a\u306e\u30c4\u30a4\u30fc\u30c8ID\u306e\u6295\u7a3f\u3092\u53d6\u5f97\u3059\u308b\u5834\u5408\nid_task = st.TweetsByIdTask('1447348840164564994')\noutput_json = st.JsonLineFileRawOutput('output_raw_id.jl')\noutput_print = st.CollectorRawOutput()\nst.TweetsByIdRunner(tweets_by_id_task=id_task, raw_data_outputs=[output_print, output_json]).run()<\/code><\/pre>\n\n\n\n
\u3069\u3061\u3089\u3082\u3001\u4e00\u5ea6\u5b9f\u884c\u3057\u305f\u3060\u3051\u3067\u6df1\u304f\u8a66\u3057\u3066\u3044\u307e\u305b\u3093\u3002\u3042\u304f\u307e\u3067\u3001\u53c2\u8003\u30c7\u30fc\u30bf\u3068\u3057\u3066\u8f09\u305b\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\n\n\n\n
WordCloud\u3067\u53ef\u8996\u5316\u3059\u308b<\/h2>\n\n\n\n
\u4ee5\u524d\u306eWordCloud\u306e\u8a18\u4e8b<\/a>\u3092\u53c2\u8003\u306b\u3001\u4e0b\u8a18\u306e\u3088\u3046\u306b\u30b3\u30fc\u30c9\u3092\u8a18\u8f09\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
import requests\nfrom bs4 import BeautifulSoup\nfrom wordcloud import WordCloud\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport numpy as np\nfrom janome.tokenizer import Tokenizer\nimport re\n\n#----Janome\u306b\u3088\u308b\u5f62\u614b\u7d20\u89e3\u6790----\n\n# Janome\u306e\u8d77\u52d5\nt = Tokenizer()\n\n# 1\u884c\u3054\u3068\u306bJanome\u306e\u7d50\u679c\u304c\u5165\u308b\ntoken = t.tokenize(text)\n\nword_list = []\n\nfor line in token:\n    # \u30b9\u30da\u30fc\u30b9\u3001\u30ab\u30f3\u30de\u3067\u30c7\u30fc\u30bf\u3092\u533a\u5207\u308b\n    tmp = re.split('\\t|,',str(line))\n\n    # tmp\u306e\u9577\u3055\u304c1\u672a\u6e80\u306e\u5834\u5408\u306f\u30b9\u30ad\u30c3\u30d7\u3059\u308b\n    if len(tmp) < 2:\n        continue\n    \n    # \u540d\u8a5e\u306e\u307f\u3001\u30ef\u30fc\u30c9\u3092\u53d6\u308a\u51fa\u3059\n    if tmp[1] == '\u540d\u8a5e':\n        word_list.append(tmp[0])\n\n# word_list\u3092\u6587\u5b57\u5217\u306b\u5909\u63db\u3059\u308b\nword_chain = ' '.join(word_list)\n\n#----WordCloud\u306b\u3088\u308b\u53ef\u8996\u5316----\n\n# \u30d5\u30a9\u30f3\u30c8\u306e\u6307\u5b9a\nfont_path = \"meiryo.ttc\"\n\n# \u9664\u5916\u30ad\u30fc\u30ef\u30fc\u30c9\nstop_words_ja = ['\u3082\u306e', '\u3053\u3068', '\u3068\u304d', '\u305d\u3046', '\u305f\u3061', '\u3053\u308c', '\u3088\u3046', '\u3053\u308c\u3089', '\u305d\u308c', '\u3059\u3079\u3066','\u306e','\u3093']\n\n# \u691c\u7d22\u30ef\u30fc\u30c9\u3001URL\u306e\u60c5\u5831\u304c\u7121\u99c4\u306b\u8ffd\u52a0\u3055\u308c\u3066\u3044\u308b\u306e\u3067\u3001\u9664\u5916\u30ad\u30fc\u30ef\u30fc\u30c9\u306b\u8ffd\u52a0\nstop_words_ja_add_1 = key_words.split()\nstop_words_ja_add_2 = ['t','https','co']\nstop_words_ja.extend(stop_words_ja_add_1)\nstop_words_ja.extend(stop_words_ja_add_2)\n\n# \u753b\u50cf\u4f5c\u6210\nwordcloud = WordCloud(width=800, height=600, font_path=font_path, background_color='white', stopwords=stop_words_ja, regexp=\"[\\w']+\").generate(word_chain)\n\n# Wordcloud\u3092\u8868\u793a\nplt.figure(figsize=(8, 6))\nplt.imshow(wordcloud)\nplt.axis('off')\nplt.show()\n\n# \u753b\u50cf\u4fdd\u5b58\n#wordcloud.to_file(\"result_wordcrowd.png\")<\/code><\/pre>\n\n\n\n
\u3053\u306e\u65e5\u306e\u30cb\u30e5\u30fc\u30b9\u3067\u3001
\u3010\u6771\u5927\u3001ChatGPT\u306a\u3069\u751f\u6210\u7cfbAI\u306b\u898b\u89e3\u3000\u300c\u4eba\u985e\u306f\u3053\u306e\u6570\u30f6\u6708\u3067\u30eb\u30d3\u30b3\u30f3\u5ddd\u3092\u6e21\u3063\u3066\u3057\u307e\u3063\u305f\u304b\u3082\u3057\u308c\u306a\u3044\u300d\u3011
\u3068\u8a00\u3046\u306e\u304c\u3042\u308a\u307e\u3057\u305f\u306e\u3067\u3001\u53cd\u6620\u3067\u304d\u3066\u3044\u308b\u306e\u304b\u3068\u3002<\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\n\n\n\n
\u3082\u3063\u3068\u4e0a\u624b\u306b\u307e\u3068\u3081\u308b\u3053\u3068\u3082\u3067\u304d\u308b\u304b\u3068\u601d\u3044\u307e\u3059\u304c\u3001\u3068\u308a\u3042\u3048\u305a\u3001\u3053\u3053\u307e\u3067\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
Twitter\u306e\u6295\u7a3f\u5185\u5bb9\u3092\u30b5\u30fc\u30c9API\u3067\u53d6\u5f97\u3059\u308b\u30e9\u30a4\u30d6\u30e9\u30eastweet\u3068\u3001\u6587\u4e2d\u306e\u51fa\u73fe\u983b\u5ea6\u306e\u9ad8\u3044\u5358\u8a9e\u3092\u62bd\u51fa\u3057\u3066\u53ef\u8996\u5316\u3059\u308b\u30c4\u30fc\u30ebWordCloud\u3092\u7528\u3044\u3066\u3001Twitter\u306e\u30c8\u30ec\u30f3\u30c9\u3092\u53ef\u8996\u5316\u3057\u3066\u307f\u307e\u3057\u305f\u3002 \u691c\u7d22\u30ad\u30fc\u30ef\u30fc\u30c9\u3092\u5909\u66f4 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[],"class_list":{"0":"post-1624","1":"post","2":"type-post","3":"status-publish","4":"format-standard","6":"category-python"},"_links":{"self":[{"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=\/wp\/v2\/posts\/1624","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1624"}],"version-history":[{"count":12,"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=\/wp\/v2\/posts\/1624\/revisions"}],"predecessor-version":[{"id":1640,"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=\/wp\/v2\/posts\/1624\/revisions\/1640"}],"wp:attachment":[{"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1624"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1624"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fukugyouhistory.tokyo\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1624"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}