scraper

Documentation

Index

• Constants
• type EdgarFullIndexScraper
  • func NewEdgarFullIndexScraper(year, quarter int, ts *tmpStore.TempStore, persister persist.PersistCompany, ...) *EdgarFullIndexScraper
  • func (efis *EdgarFullIndexScraper) GetXbrl(edgarFilename, bucket, fileKey string, reportFile *filings.ReportFile)
  • func (efis *EdgarFullIndexScraper) ParseIndexFile(fileReader io.ReadCloser)
  • func (efis *EdgarFullIndexScraper) ScrapeEdgarQuarterlyIndex()

Constants

const EDGAR_FULL_INDEX_URL_PREFIX = "http://www.sec.gov/Archives/edgar/full-index/"

const INDEX_FILE_NAME = "/xbrl.idx"

const SEC_EDGAR_BASE_URL = "http://www.sec.gov/Archives/"

const XBRL_ZIP_SUFFIX = "-xbrl.zip"

Types

type EdgarFullIndexScraper

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

func NewEdgarFullIndexScraper

func NewEdgarFullIndexScraper(year, quarter int,
	ts *tmpStore.TempStore, persister persist.PersistCompany,
	reportPersister persist.PersistReportFiles) *EdgarFullIndexScraper

func (*EdgarFullIndexScraper) GetXbrl

func (efis *EdgarFullIndexScraper) GetXbrl(edgarFilename, bucket, fileKey string, reportFile *filings.ReportFile)

The full index provides links to txt files. We want to convert these to retrieve the corresponding zip of xbrl files and extract the main xbrl file.

func (*EdgarFullIndexScraper) ParseIndexFile

func (efis *EdgarFullIndexScraper) ParseIndexFile(fileReader io.ReadCloser)

Parses a ReadCloser that contains a Full Index file. The caller is responsible for closing the ReadCloser.

func (*EdgarFullIndexScraper) ScrapeEdgarQuarterlyIndex

func (efis *EdgarFullIndexScraper) ScrapeEdgarQuarterlyIndex()