├── README.md ├── SJTUbbsSpiderDemo ├── bbs │ ├── __init__.py │ ├── __init__.pyc │ ├── items.py │ ├── items.pyc │ ├── pipelines.py │ ├── pipelines.pyc │ ├── settings.py │ ├── settings.pyc │ └── spiders │ │ ├── __init__.py │ │ ├── __init__.pyc │ │ ├── forumSpider.py │ │ └── forumSpider.pyc ├── dataProcess.py ├── dataProcess.pyc └── scrapy.cfg └── gouwu.sogou.com ├── etao ├── __init__.py ├── __init__.pyc ├── items.py ├── items.pyc ├── lstData.py ├── lstData.pyc ├── pipelines.py ├── pipelines.pyc ├── settings.py ├── settings.pyc └── spiders │ ├── __init__.py │ ├── __init__.pyc │ ├── spider.py │ └── spider.pyc ├── scrapy.cfg └── webData.xml /README.md: -------------------------------------------------------------------------------- 1 | # spiderDemo 2 | Crawlers for several Websites. 3 | -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/__init__.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/items.py -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/items.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/items.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/pipelines.py -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/pipelines.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/pipelines.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/settings.py -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/settings.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/settings.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/spiders/__init__.py -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/spiders/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/spiders/__init__.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/spiders/forumSpider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/spiders/forumSpider.py -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/bbs/spiders/forumSpider.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/bbs/spiders/forumSpider.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/dataProcess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/dataProcess.py -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/dataProcess.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/dataProcess.pyc -------------------------------------------------------------------------------- /SJTUbbsSpiderDemo/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/SJTUbbsSpiderDemo/scrapy.cfg -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/__init__.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/items.py -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/items.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/items.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/lstData.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/lstData.py -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/lstData.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/lstData.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/pipelines.py -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/pipelines.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/pipelines.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/settings.py -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/settings.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/settings.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/spiders/__init__.py -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/spiders/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/spiders/__init__.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/spiders/spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/spiders/spider.py -------------------------------------------------------------------------------- /gouwu.sogou.com/etao/spiders/spider.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/etao/spiders/spider.pyc -------------------------------------------------------------------------------- /gouwu.sogou.com/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/scrapy.cfg -------------------------------------------------------------------------------- /gouwu.sogou.com/webData.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chenqx/spiderDemo/HEAD/gouwu.sogou.com/webData.xml --------------------------------------------------------------------------------