├── .gitignore ├── LICENSE ├── README.md ├── TaiwanNewsCrawler ├── __init__.py ├── items.py ├── pipelines.py ├── settings.py └── spiders │ ├── __init__.py │ ├── apple_realtimenews_spider.py │ ├── apple_spider.py │ ├── china_spider.py │ ├── cna_spider.py │ ├── cts_spider.py │ ├── ettoday_spider.py │ ├── ettoday_tag_spider.py │ ├── liberty_realtimenews_spider.py │ ├── liberty_spider.py │ ├── liberty_tag_spider.py │ ├── pts_spider.py │ ├── setn_spider.py │ ├── tvbs_spider.py │ └── udn_spider.py ├── requirements.txt └── scrapy.cfg /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/README.md -------------------------------------------------------------------------------- /TaiwanNewsCrawler/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /TaiwanNewsCrawler/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/items.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/pipelines.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/settings.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/__init__.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/apple_realtimenews_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/apple_realtimenews_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/apple_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/apple_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/china_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/china_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/cna_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/cna_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/cts_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/cts_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/ettoday_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/ettoday_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/ettoday_tag_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/ettoday_tag_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/liberty_realtimenews_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/liberty_realtimenews_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/liberty_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/liberty_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/liberty_tag_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/liberty_tag_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/pts_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/pts_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/setn_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/setn_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/tvbs_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/tvbs_spider.py -------------------------------------------------------------------------------- /TaiwanNewsCrawler/spiders/udn_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/TaiwanNewsCrawler/spiders/udn_spider.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | scrapy==1.3.0 2 | Twisted==16.6.0 -------------------------------------------------------------------------------- /scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TaiwanStat/Taiwan-news-crawlers/HEAD/scrapy.cfg --------------------------------------------------------------------------------