{"id":22904029,"url":"https://github.com/ftes/ocr-drive","last_synced_at":"2025-04-01T07:57:02.761Z","repository":{"id":10328768,"uuid":"12458916","full_name":"ftes/ocr-drive","owner":"ftes","description":"Perform OCR locally on a linux machine in combination with Google Drive for document storage","archived":false,"fork":false,"pushed_at":"2013-09-15T16:43:51.000Z","size":120,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-07T04:42:15.019Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ftes.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2013-08-29T11:52:49.000Z","updated_at":"2013-09-15T16:43:52.000Z","dependencies_parsed_at":"2022-08-31T07:11:52.536Z","dependency_job_id":null,"html_url":"https://github.com/ftes/ocr-drive","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/ftes%2Focr-drive","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ftes%2Focr-drive/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ftes%2Focr-drive/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ftes%2Focr-drive/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ftes","download_url":"https://codeload.github.com/ftes/ocr-drive/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246604618,"owners_count":20804100,"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":"2024-12-14T02:39:58.080Z","updated_at":"2025-04-01T07:57:02.730Z","avatar_url":"https://github.com/ftes.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"ocr-drive\n=========\n\nPerform OCR locally on a Unix machine in combination with Google Drive for document storage.\nWhile the python scripts are platform independent, for now `pdfsandwich` is used as a wrapper script\nfor performing OCR on PDF files and embedding the results back into the PDF, and is therefore only\navailable for Unix systems.\n\n\nDependencies\n------------\nThe following software must be installed for the scripts to work:\n* [pdfsandwich](http://www.tobias-elze.de/pdfsandwich/index.html)\n* [python 2](http://wiki.ubuntuusers.de/Python)\n* [Google Drive python SDK](https://developers.google.com/drive/quickstart-python)\n\n\nUsage\n-----\n\n1. [Enable](https://developers.google.com/drive/quickstart-python#step_2_install_the_google_client_library) both the Drive SDK and Drive API in the Google API Console.\n2. Save your API credentials in `client-secrets.json`, the syntax for which is shown in [authorize.py](authorize.py).\n3. Run the `authorize.py` script, which will provide you with a URL to visit and access an authorization code.\n4. Add the [process.sh](process.sh) and [download-for-ocr.py](download-for-ocr.py) scripts to your incron (run `incrontab -e`) and cron (run `crontab -e`) tables, so they run automatically.\nExample configurations are included as comments at the beginning of both files.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fftes%2Focr-drive","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fftes%2Focr-drive","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fftes%2Focr-drive/lists"}