├── README.md ├── core ├── README ├── gooseeker-2.1.zip └── gooseeker.py ├── crawler ├── README ├── anjuke.py ├── crawl_gooseeker_bbs.py ├── douban.py ├── result1.xml ├── result2.xml ├── simpleSpider │ ├── __pycache__ │ │ └── gooseeker.cpython-35.pyc │ ├── gooseeker.py │ ├── scrapy.cfg │ └── simpleSpider │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-35.pyc │ │ └── settings.cpython-35.pyc │ │ ├── items.py │ │ ├── pipelines.py │ │ ├── settings.py │ │ └── spiders │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-35.pyc │ │ ├── gooseeker.cpython-35.pyc │ │ └── simplespider.cpython-35.pyc │ │ └── simplespider.py ├── tmSpider │ ├── scrapy.cfg │ └── tmSpider │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-35.pyc │ │ ├── downloader.cpython-35.pyc │ │ └── settings.cpython-35.pyc │ │ ├── gooseeker │ │ ├── __pycache__ │ │ │ └── gsextractor.cpython-35.pyc │ │ └── gsextractor.py │ │ ├── items.py │ │ ├── middlewares │ │ ├── __pycache__ │ │ │ ├── downloader.cpython-35.pyc │ │ │ └── middleware.cpython-35.pyc │ │ ├── downloader.py │ │ └── middleware.py │ │ ├── pipelines.py │ │ ├── settings.py │ │ └── spiders │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-35.pyc │ │ ├── runcrawl.cpython-35.pyc │ │ └── tmall.cpython-35.pyc │ │ ├── runcrawl.py │ │ └── tmall.py └── xslt_bbs.xml ├── docs └── README.MD └── test ├── README └── readPdf.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/README.md -------------------------------------------------------------------------------- /core/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/core/README -------------------------------------------------------------------------------- /core/gooseeker-2.1.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/core/gooseeker-2.1.zip -------------------------------------------------------------------------------- /core/gooseeker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/core/gooseeker.py -------------------------------------------------------------------------------- /crawler/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/README -------------------------------------------------------------------------------- /crawler/anjuke.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/anjuke.py -------------------------------------------------------------------------------- /crawler/crawl_gooseeker_bbs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/crawl_gooseeker_bbs.py -------------------------------------------------------------------------------- /crawler/douban.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/douban.py -------------------------------------------------------------------------------- /crawler/result1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/result1.xml -------------------------------------------------------------------------------- /crawler/result2.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/result2.xml -------------------------------------------------------------------------------- /crawler/simpleSpider/__pycache__/gooseeker.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/__pycache__/gooseeker.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/simpleSpider/gooseeker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/gooseeker.py -------------------------------------------------------------------------------- /crawler/simpleSpider/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/scrapy.cfg -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/__pycache__/settings.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/__pycache__/settings.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/items.py -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/pipelines.py -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/settings.py -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/spiders/__init__.py -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/spiders/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/spiders/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/spiders/__pycache__/gooseeker.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/spiders/__pycache__/gooseeker.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/spiders/__pycache__/simplespider.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/spiders/__pycache__/simplespider.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/simpleSpider/simpleSpider/spiders/simplespider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/simpleSpider/simpleSpider/spiders/simplespider.py -------------------------------------------------------------------------------- /crawler/tmSpider/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/scrapy.cfg -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/__pycache__/downloader.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/__pycache__/downloader.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/__pycache__/settings.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/__pycache__/settings.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/gooseeker/__pycache__/gsextractor.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/gooseeker/__pycache__/gsextractor.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/gooseeker/gsextractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/gooseeker/gsextractor.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/items.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/middlewares/__pycache__/downloader.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/middlewares/__pycache__/downloader.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/middlewares/__pycache__/middleware.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/middlewares/__pycache__/middleware.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/middlewares/downloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/middlewares/downloader.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/middlewares/middleware.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/middlewares/middleware.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/pipelines.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/settings.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/spiders/__init__.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/spiders/__pycache__/__init__.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/spiders/__pycache__/__init__.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/spiders/__pycache__/runcrawl.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/spiders/__pycache__/runcrawl.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/spiders/__pycache__/tmall.cpython-35.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/spiders/__pycache__/tmall.cpython-35.pyc -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/spiders/runcrawl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/spiders/runcrawl.py -------------------------------------------------------------------------------- /crawler/tmSpider/tmSpider/spiders/tmall.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/tmSpider/tmSpider/spiders/tmall.py -------------------------------------------------------------------------------- /crawler/xslt_bbs.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/crawler/xslt_bbs.xml -------------------------------------------------------------------------------- /docs/README.MD: -------------------------------------------------------------------------------- 1 | Created on May 26,2016 2 | -------------------------------------------------------------------------------- /test/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/test/README -------------------------------------------------------------------------------- /test/readPdf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FullerHua/gooseeker/HEAD/test/readPdf.py --------------------------------------------------------------------------------