| Filename | Size | Update |
|---|
| news-please-master | 0 | 2017-12-03
|
| news-please-master\.gitignore | 135 | 2017-12-03
|
| news-please-master\CODE_OF_CONDUCT.md | 3226 | 2017-12-03
|
| news-please-master\CONTRIBUTING.md | 288 | 2017-12-03
|
| news-please-master\LICENSE.txt | 11356 | 2017-12-03
|
| news-please-master\MANIFEST.in | 182 | 2017-12-03
|
| news-please-master\README.md | 10402 | 2017-12-03
|
| news-please-master\misc | 0 | 2017-12-03
|
| news-please-master\misc\logo | 0 | 2017-12-03
|
| news-please-master\misc\logo\logo-128.png | 1938 | 2017-12-03
|
| news-please-master\misc\logo\logo-256.png | 3589 | 2017-12-03
|
| news-please-master\misc\logo\logo.svg | 2280 | 2017-12-03
|
| news-please-master\newsplease | 0 | 2017-12-03
|
| news-please-master\newsplease\NewsArticle.py | 1212 | 2017-12-03
|
| news-please-master\newsplease\__init__.py | 4315 | 2017-12-03
|
| news-please-master\newsplease\__main__.py | 22179 | 2017-12-03
|
| news-please-master\newsplease\config.py | 9201 | 2017-12-03
|
| news-please-master\newsplease\config | 0 | 2017-12-03
|
| news-please-master\newsplease\config\config.cfg | 14044 | 2017-12-03
|
| news-please-master\newsplease\config\config_lib.cfg | 14338 | 2017-12-03
|
| news-please-master\newsplease\config\sitelist.hjson | 2127 | 2017-12-03
|
| news-please-master\newsplease\crawler | 0 | 2017-12-03
|
| news-please-master\newsplease\crawler\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\crawler\commoncrawl_crawler.py | 10097 | 2017-12-03
|
| news-please-master\newsplease\crawler\commoncrawl_extractor.py | 13916 | 2017-12-03
|
| news-please-master\newsplease\crawler\items.py | 1450 | 2017-12-03
|
| news-please-master\newsplease\crawler\simple_crawler.py | 1468 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders | 0 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders\__init__.py | 161 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders\download_crawler.py | 1242 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders\recursive_crawler.py | 1889 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders\recursive_sitemap_crawler.py | 2133 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders\rss_crawler.py | 3056 | 2017-12-03
|
| news-please-master\newsplease\crawler\spiders\sitemap_crawler.py | 2037 | 2017-12-03
|
| news-please-master\newsplease\examples | 0 | 2017-12-03
|
| news-please-master\newsplease\examples\commoncrawl.py | 5905 | 2017-12-03
|
| news-please-master\newsplease\examples\downloadfromfile.py | 707 | 2017-12-03
|
| news-please-master\newsplease\examples\downloadfromurl.py | 534 | 2017-12-03
|
| news-please-master\newsplease\examples\sample.json | 5635 | 2017-12-03
|
| news-please-master\newsplease\helper.py | 1177 | 2017-12-03
|
| news-please-master\newsplease\helper_classes | 0 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\heuristics.py | 4703 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\parse_crawler.py | 4718 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\savepath_parser.py | 11381 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\sub_classes | 0 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\sub_classes\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\sub_classes\heuristics_manager.py | 9827 | 2017-12-03
|
| news-please-master\newsplease\helper_classes\url_extractor.py | 6009 | 2017-12-03
|
| news-please-master\newsplease\pipeline | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\article_candidate.py | 362 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\article_extractor.py | 2549 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\cleaner.py | 3464 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer.py | 1960 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_Language.py | 1933 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_author.py | 1349 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_date.py | 1274 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_description.py | 1411 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_text.py | 3329 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_title.py | 3072 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\comparer\comparer_topimage.py | 1865 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors\__init__.py | 0 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors\abstract_extractor.py | 2011 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors\date_extractor.py | 8356 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors\lang_detect_extractor.py | 2533 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors\newspaper_extractor.py | 1671 | 2017-12-03
|
| news-please-master\newsplease\pipeline\extractor\extractors\readability_extractor.py | 1306 | 2017-12-03
|
| news-please-master\newsplease\pipeline\pipelines.py | 22793 | 2017-12-03
|
| news-please-master\newsplease\single_crawler.py | 10325 | 2017-12-03
|
| news-please-master\requirements.txt | 431 | 2017-12-03
|
| news-please-master\setup.py | 3228 | 2017-12-03 |