├── .gitignore ├── .gitmodules ├── README.md ├── app ├── Crawler.php ├── Curl.php ├── Html_scraper.php ├── helpers │ └── states_array.php └── models │ ├── Webpage.php │ └── Website.php ├── config_sample.php ├── inputs ├── .gitignore ├── targets_example.csv └── terms_example.csv ├── process_targets.php ├── results └── .gitignore └── utilities ├── previous_target_csvs ├── 012214-ca-or-wa-edcs.csv ├── 012214-ccr-vendors-results.csv ├── 012214-ccr-vendors.csv ├── 012814-ccr-vendors-results-for-kma.csv ├── 012814-logistics-results-for-insightly.csv ├── 012814-logistics-results-for-kma.csv └── 012814-logistics-targets.csv └── target_scrapers ├── README.md └── ecodevdirectory.com ├── README.md ├── full_results.csv ├── listing_page.html └── scrape_edc_state.php /.gitignore: -------------------------------------------------------------------------------- 1 | config.php -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/.gitmodules -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/README.md -------------------------------------------------------------------------------- /app/Crawler.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/app/Crawler.php -------------------------------------------------------------------------------- /app/Curl.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/app/Curl.php -------------------------------------------------------------------------------- /app/Html_scraper.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/app/Html_scraper.php -------------------------------------------------------------------------------- /app/helpers/states_array.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/app/helpers/states_array.php -------------------------------------------------------------------------------- /app/models/Webpage.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/app/models/Webpage.php -------------------------------------------------------------------------------- /app/models/Website.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/app/models/Website.php -------------------------------------------------------------------------------- /config_sample.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/config_sample.php -------------------------------------------------------------------------------- /inputs/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/inputs/.gitignore -------------------------------------------------------------------------------- /inputs/targets_example.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/inputs/targets_example.csv -------------------------------------------------------------------------------- /inputs/terms_example.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/inputs/terms_example.csv -------------------------------------------------------------------------------- /process_targets.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/process_targets.php -------------------------------------------------------------------------------- /results/.gitignore: -------------------------------------------------------------------------------- 1 | *.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012214-ca-or-wa-edcs.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012214-ca-or-wa-edcs.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012214-ccr-vendors-results.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012214-ccr-vendors-results.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012214-ccr-vendors.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012214-ccr-vendors.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012814-ccr-vendors-results-for-kma.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012814-ccr-vendors-results-for-kma.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012814-logistics-results-for-insightly.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012814-logistics-results-for-insightly.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012814-logistics-results-for-kma.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012814-logistics-results-for-kma.csv -------------------------------------------------------------------------------- /utilities/previous_target_csvs/012814-logistics-targets.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/previous_target_csvs/012814-logistics-targets.csv -------------------------------------------------------------------------------- /utilities/target_scrapers/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/target_scrapers/README.md -------------------------------------------------------------------------------- /utilities/target_scrapers/ecodevdirectory.com/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/target_scrapers/ecodevdirectory.com/README.md -------------------------------------------------------------------------------- /utilities/target_scrapers/ecodevdirectory.com/full_results.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/target_scrapers/ecodevdirectory.com/full_results.csv -------------------------------------------------------------------------------- /utilities/target_scrapers/ecodevdirectory.com/listing_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/target_scrapers/ecodevdirectory.com/listing_page.html -------------------------------------------------------------------------------- /utilities/target_scrapers/ecodevdirectory.com/scrape_edc_state.php: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tbrianjones/website_extractor/HEAD/utilities/target_scrapers/ecodevdirectory.com/scrape_edc_state.php --------------------------------------------------------------------------------