Added an EU Supply source, scraping the UK portal's public tenders
internal/eusupply replaces the old Node scraper (eu-supply.js) for uk.eu-supply.com. The site has no API, so it posts the public search form, which now needs the form's current defaults and reads the HTML with golang.org/x/net/html. Each tender not stored yet has its own page read too, for its description, contract type, CPV codes and buyer address. Tenders are stored with the source "EU Supply - UK" as eusupply-uk-<tender id>, with one release holding the tender as read. The site publishes no rate limit, so the client sets its own: one request at a time, with a random wait between sources.eu_supply.request_min_gap and request_max_gap (2s to 10s). The source has the same 7-day backfill as Find a Tender's. Most of its tenders are also on Find a Tender, so a new one is stored Hidden and Skipped when another source's opportunity released within 30 days has a title at least 90% alike, and its buyer or description matches too (80% of the shorter one's significant words).
This commit is contained in:
1 parent
5c62376b6e
commit
3a06132071
25 files changed
+2520
-8
No files matched your search
@@ -1041,6 +1041,37 @@ func (s *Store) LatestReleaseDate(
|
||||
return latest, nil
|
||||
}
|
||||
|
||||
// OpportunityTitle is an opportunity's UUID, title and latest release date,
|
||||
// as ListOtherSourcesTitles lists them.
|
||||
type OpportunityTitle struct {
|
||||
UUID string `db:"uuid"`
|
||||
Title string `db:"title"`
|
||||
LatestReleaseDate time.Time `db:"latest_release_date"`
|
||||
}
|
||||
|
||||
// ListOtherSourcesTitles returns the UUID, title and latest release date of
|
||||
// every opportunity not from source whose latest release is from from
|
||||
// (inclusive) to before (exclusive), so a fetcher can find the ones a new
|
||||
// opportunity repeats.
|
||||
func (s *Store) ListOtherSourcesTitles(
|
||||
ctx context.Context, source string, from, before time.Time,
|
||||
) ([]OpportunityTitle, error) {
|
||||
titles := []OpportunityTitle{}
|
||||
err := s.db.SelectContext(
|
||||
ctx,
|
||||
&titles,
|
||||
selectOtherSourcesTitles,
|
||||
source,
|
||||
from.UTC(),
|
||||
before.UTC(),
|
||||
)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("listing titles of sources but %s: %w", source, err)
|
||||
}
|
||||
|
||||
return titles, nil
|
||||
}
|
||||
|
||||
// ReleaseExists reports whether a release is already stored, so a fetcher
|
||||
// can skip converting it.
|
||||
func (s *Store) ReleaseExists(
|
||||
|
||||
Reference in new issue
Block a user