doubangroup

Documentation

Index

• Constants
• Variables
• func GetSunRoom(ctx *spider.Context) (spider.ParseResult, error)
• func ParseURL(ctx *spider.Context) (spider.ParseResult, error)

Constants

const ContentRe = `<div class="topic-content">[\s\S]*?阳台[\s\S]*?<div class="aside">`

Variables

var GroupTask = &spider.Task{
	Rule: spider.RuleTree{
		Root: func() ([]*spider.Request, error) {
			var roots []*spider.Request
			for i := 0; i < 25; i += 25 {
				str := fmt.Sprintf("https://www.douban.com/group/szsh/discussion?start=%d", i)
				roots = append(roots, &spider.Request{
					Priority: 1,
					URL:      str,
					Method:   "GET",
					RuleName: "解析网站URL",
				})
			}

			return roots, nil
		},
		Trunk: map[string]*spider.Rule{
			"解析网站URL": {ParseFunc: ParseURL},
			"解析阳台房":   {ParseFunc: GetSunRoom},
		},
	},
}

Functions

func GetSunRoom

func GetSunRoom(ctx *spider.Context) (spider.ParseResult, error)

func ParseURL

func ParseURL(ctx *spider.Context) (spider.ParseResult, error)