├── .gitignore ├── README.md ├── cassettes ├── .gitignore └── README.md ├── convert_json_to_csv.py ├── crawl_all.sh ├── crawl_single_episode.sh ├── female_names.txt ├── male_names.txt ├── output ├── actors.csv ├── actors.json ├── appearances.csv ├── appearances.json ├── casts.csv ├── casts.json ├── characters.csv ├── characters.json ├── episodes.csv ├── episodes.json ├── hosts.csv ├── hosts.json ├── impressions.csv ├── impressions.json ├── seasons.csv ├── seasons.json ├── sketches.csv ├── sketches.json ├── tenure.csv ├── titles.csv └── titles.json ├── requirements.txt ├── scrapy.cfg ├── single_ep_output ├── actors.json ├── appearances.json ├── characters.json ├── episodes.json ├── hosts.json ├── impressions.json ├── seasons.json ├── sketches.json └── titles.json ├── snl.html ├── snl.ipynb ├── snl_analysis.html ├── snl_analysis.ipynb ├── snl_records.html ├── snl_records.ipynb ├── snl_records.md ├── snl_records_season.html ├── snl_records_season.ipynb └── snlscrape ├── __init__.py ├── conftest.py ├── crawl_test_helpers.py ├── format.py ├── helpers.py ├── items.py ├── pipelines.py ├── settings.py ├── settings_testing.py ├── spiders ├── __init__.py ├── cast.py └── snl.py ├── test_cast_spider.py └── test_crawl.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/README.md -------------------------------------------------------------------------------- /cassettes/.gitignore: -------------------------------------------------------------------------------- 1 | *.json 2 | -------------------------------------------------------------------------------- /cassettes/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/cassettes/README.md -------------------------------------------------------------------------------- /convert_json_to_csv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/convert_json_to_csv.py -------------------------------------------------------------------------------- /crawl_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/crawl_all.sh -------------------------------------------------------------------------------- /crawl_single_episode.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/crawl_single_episode.sh -------------------------------------------------------------------------------- /female_names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/female_names.txt -------------------------------------------------------------------------------- /male_names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/male_names.txt -------------------------------------------------------------------------------- /output/actors.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/actors.csv -------------------------------------------------------------------------------- /output/actors.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/actors.json -------------------------------------------------------------------------------- /output/appearances.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/appearances.csv -------------------------------------------------------------------------------- /output/appearances.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/appearances.json -------------------------------------------------------------------------------- /output/casts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/casts.csv -------------------------------------------------------------------------------- /output/casts.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/casts.json -------------------------------------------------------------------------------- /output/characters.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/characters.csv -------------------------------------------------------------------------------- /output/characters.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/characters.json -------------------------------------------------------------------------------- /output/episodes.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/episodes.csv -------------------------------------------------------------------------------- /output/episodes.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/episodes.json -------------------------------------------------------------------------------- /output/hosts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/hosts.csv -------------------------------------------------------------------------------- /output/hosts.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/hosts.json -------------------------------------------------------------------------------- /output/impressions.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/impressions.csv -------------------------------------------------------------------------------- /output/impressions.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/impressions.json -------------------------------------------------------------------------------- /output/seasons.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/seasons.csv -------------------------------------------------------------------------------- /output/seasons.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/seasons.json -------------------------------------------------------------------------------- /output/sketches.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/sketches.csv -------------------------------------------------------------------------------- /output/sketches.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/sketches.json -------------------------------------------------------------------------------- /output/tenure.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/tenure.csv -------------------------------------------------------------------------------- /output/titles.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/titles.csv -------------------------------------------------------------------------------- /output/titles.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/output/titles.json -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/requirements.txt -------------------------------------------------------------------------------- /scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/scrapy.cfg -------------------------------------------------------------------------------- /single_ep_output/actors.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/actors.json -------------------------------------------------------------------------------- /single_ep_output/appearances.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/appearances.json -------------------------------------------------------------------------------- /single_ep_output/characters.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/characters.json -------------------------------------------------------------------------------- /single_ep_output/episodes.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/episodes.json -------------------------------------------------------------------------------- /single_ep_output/hosts.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/hosts.json -------------------------------------------------------------------------------- /single_ep_output/impressions.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/impressions.json -------------------------------------------------------------------------------- /single_ep_output/seasons.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/seasons.json -------------------------------------------------------------------------------- /single_ep_output/sketches.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/sketches.json -------------------------------------------------------------------------------- /single_ep_output/titles.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/single_ep_output/titles.json -------------------------------------------------------------------------------- /snl.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl.html -------------------------------------------------------------------------------- /snl.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl.ipynb -------------------------------------------------------------------------------- /snl_analysis.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_analysis.html -------------------------------------------------------------------------------- /snl_analysis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_analysis.ipynb -------------------------------------------------------------------------------- /snl_records.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_records.html -------------------------------------------------------------------------------- /snl_records.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_records.ipynb -------------------------------------------------------------------------------- /snl_records.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_records.md -------------------------------------------------------------------------------- /snl_records_season.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_records_season.html -------------------------------------------------------------------------------- /snl_records_season.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snl_records_season.ipynb -------------------------------------------------------------------------------- /snlscrape/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /snlscrape/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/conftest.py -------------------------------------------------------------------------------- /snlscrape/crawl_test_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/crawl_test_helpers.py -------------------------------------------------------------------------------- /snlscrape/format.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/format.py -------------------------------------------------------------------------------- /snlscrape/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/helpers.py -------------------------------------------------------------------------------- /snlscrape/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/items.py -------------------------------------------------------------------------------- /snlscrape/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/pipelines.py -------------------------------------------------------------------------------- /snlscrape/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/settings.py -------------------------------------------------------------------------------- /snlscrape/settings_testing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/settings_testing.py -------------------------------------------------------------------------------- /snlscrape/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/spiders/__init__.py -------------------------------------------------------------------------------- /snlscrape/spiders/cast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/spiders/cast.py -------------------------------------------------------------------------------- /snlscrape/spiders/snl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/spiders/snl.py -------------------------------------------------------------------------------- /snlscrape/test_cast_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/test_cast_spider.py -------------------------------------------------------------------------------- /snlscrape/test_crawl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hhllcks/snldb/HEAD/snlscrape/test_crawl.py --------------------------------------------------------------------------------