├── .gitignore ├── README.md ├── crawlBaidubaike ├── crawlBaidubaike │ ├── __init__.py │ ├── autoproxy.py │ ├── baidubaikeItem.py │ ├── baidubaikePipelines.py │ ├── items.py │ ├── middlewares.py │ ├── pipelines.py │ ├── settings.py │ └── spiders │ │ ├── __init__.py │ │ ├── baidubaike_spider.py │ │ └── collectStartUrls.py ├── scrapy.cfg └── start_urls.txt ├── hudongbaike ├── .gitignore ├── hudongbaike │ ├── __init__.py │ ├── __init__.pyc │ ├── autoproxy.py │ ├── autoproxy.pyc │ ├── items.py │ ├── items.pyc │ ├── middlewares.py │ ├── pipelines.py │ ├── pipelines.pyc │ ├── settings.py │ ├── settings.pyc │ └── spiders │ │ ├── __init__.py │ │ ├── __init__.pyc │ │ ├── main_spider.py │ │ └── main_spider.pyc └── scrapy.cfg ├── link_by_entity_name.py └── preprocess.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ 2 | data/ 3 | result/ -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # openkg-link 2 | -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/autoproxy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/autoproxy.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/baidubaikeItem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/baidubaikeItem.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/baidubaikePipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/baidubaikePipelines.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/items.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/middlewares.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/middlewares.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/pipelines.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/settings.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/spiders/__init__.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/spiders/baidubaike_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/spiders/baidubaike_spider.py -------------------------------------------------------------------------------- /crawlBaidubaike/crawlBaidubaike/spiders/collectStartUrls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/crawlBaidubaike/spiders/collectStartUrls.py -------------------------------------------------------------------------------- /crawlBaidubaike/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/scrapy.cfg -------------------------------------------------------------------------------- /crawlBaidubaike/start_urls.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/crawlBaidubaike/start_urls.txt -------------------------------------------------------------------------------- /hudongbaike/.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/__init__.pyc -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/autoproxy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/autoproxy.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/autoproxy.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/autoproxy.pyc -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/items.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/items.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/items.pyc -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/middlewares.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/middlewares.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/pipelines.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/pipelines.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/pipelines.pyc -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/settings.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/settings.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/settings.pyc -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/spiders/__init__.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/spiders/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/spiders/__init__.pyc -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/spiders/main_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/spiders/main_spider.py -------------------------------------------------------------------------------- /hudongbaike/hudongbaike/spiders/main_spider.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/hudongbaike/spiders/main_spider.pyc -------------------------------------------------------------------------------- /hudongbaike/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/hudongbaike/scrapy.cfg -------------------------------------------------------------------------------- /link_by_entity_name.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/link_by_entity_name.py -------------------------------------------------------------------------------- /preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NoTwice1/openkg-link/HEAD/preprocess.py --------------------------------------------------------------------------------