{"id":16022010,"url":"https://github.com/cfstras/talkateev","last_synced_at":"2026-05-12T19:12:14.905Z","repository":{"id":16604066,"uuid":"19358721","full_name":"cfstras/talkateev","owner":"cfstras","description":"markov chains for twitter and libpurple, in go","archived":false,"fork":false,"pushed_at":"2014-05-01T21:41:55.000Z","size":116,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-16T18:36:05.753Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cfstras.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2014-05-01T21:41:28.000Z","updated_at":"2017-08-06T09:24:05.000Z","dependencies_parsed_at":"2022-07-13T11:40:34.456Z","dependency_job_id":null,"html_url":"https://github.com/cfstras/talkateev","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfstras%2Ftalkateev","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfstras%2Ftalkateev/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfstras%2Ftalkateev/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfstras%2Ftalkateev/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cfstras","download_url":"https://codeload.github.com/cfstras/talkateev/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242163952,"owners_count":20082228,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-08T18:20:27.386Z","updated_at":"2026-05-12T19:12:14.874Z","avatar_url":"https://github.com/cfstras.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# talkateev\n\nIs a small markov chain implementation which supports twitter and libpurple chatlogs.\nThis means you can have endless hours of fun creating conversations from your pidgin or adium logs or random twitter accounts. Also it doubles as a twitter scraper.\n\nHave fun with it!\n\nAlso, props to ChimeraCoder for building anaconda!\n\n\n## Setup\n\n    go get github.com/cfstras/talkateev\n\n## Usage\n\n    talkateev -help # helps sometimes.\n\n### With libpurple/pidgin/adium logs\n\n    talkateev -purple ~/.purple/logs\n\nThis will load logs from your libpurple (or pidgin, adium, gajim, etc), to train a markov chain and generate some output.\nThe log data is stripped from the most useless stuff (such as logon/logoff messages, partychat ramble etc) while loading. Your logs will not be edited or written in any way.\n\n### With twitter user\n\nFor twitter access, create an app on [apps.twitter.com](https://apps.twitter.com/), create an authentication token and then create a file called `auth.json` in your current directory with these contents:\n\n    {\n      \"ConsumerKey\": \"\u003cyour app API Key here\u003e\",\n      \"ConsumerSecret\": \"\u003cyour app API Secret here\u003e\",\n      \"AccessToken\": \"\u003cyour Access Token here\u003e\",\n      \"AccessSecret\": \"\u003cyour Access Token Secret here\u003e\"\n    }\n\nThen, run\n\n    talkateev -twitter \u003cyour twitter handle\u003e\n\nThis will load up _all_ tweets from that twitter user, save them in `twitter_\u003chandle\u003e.json` and then train a markov chain and some output.  \nYou can later use this downloaded data with the `-json` flag, see below.\n\n### With already downloaded twitter data\n\n    talkateev -json twitter_\u003cusername\u003e.json\n\nThis will load tweets from a json file, train a markov chain and generate some output.\n\n### some more flags\n\n`-maxLen x`: maximum sentence length in words\n`-prefixLen x`: length of prefix to search (low means less sense, but more randomness, too high (\u003e3 for 1k tweets) will result in just the tweets)\n\n\n## Development\n\nIf you want to hack on talkateev, go ahead!  \nI have provided a Makefile, so you can jump right in:\n\n    make deps\n    make start\n\nPull requests and comments welcome!\n\n## License\n\nBeerware!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcfstras%2Ftalkateev","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcfstras%2Ftalkateev","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcfstras%2Ftalkateev/lists"}