scraper

package

v0.0.0-...-4e43b7b Latest Latest Go to latest Published: Jun 9, 2023 License: MIT Imports: 15 Imported by: 0

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

This section is empty.

This section is empty.

func GetTextLength(text string) int

func HandleHttpStatusErr(res *http.Response) error

func Preprocessing(text string) string

func RemoveSimilar(arr []models.TweetArticle, threshold float64) []models.TweetArticle

type AccessToken struct {
	Token string
}

type Scraper struct {
	AccessToken
	Twitter
	Worker
	// contains filtered or unexported fields
}

func NewScraper(token string, db *db.Database, workerId string) *Scraper

func (s Scraper) CreateHttpReq(url string) (string, error)

func (s Scraper) GetRecentSearch(keyword string, nextToken string, injectNum ...int) ([]models.TweetArticle, error)

func (s Scraper) MakeUniqueArticle(jobId string) error

func (s Scraper) MakeUniqueTweet(list []models.TweetArticle) []models.TweetArticle

func (s Scraper) WriteTweetOnDB(tweet models.TweetArticle) error

type Twitter interface {
	GetRecentSearch(keyword string) ([]models.TweetArticle, error)
	GetFullArchiveRecentSearch(keyword string) error
}

type Worker struct {
	// contains filtered or unexported fields
}

Path	Synopsis
env