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:
bwilliams committed 2026-10-21 13:57:54 +01:00
1 parent 5c62376b6e
commit 3a06132071
25 files changed
+2520 -8

No files matched your search

+101
View File
@@ -0,0 +1,101 @@
package eusupply
import (
"encoding/json"
"strings"
"git.avsdev.uk/Go/job-search/internal/types"
)
// The opportunities Convert makes.
const (
// UUIDPrefix starts the UUID of every opportunity from the UK portal;
// the tender's id follows it.
UUIDPrefix = "eusupply-uk-"
// uuidType is their UUIDType.
uuidType = "eusupply"
// releaseTag is their one release's tag: the portal lists open tenders.
releaseTag = "tender"
)
// mainCategories maps the portal's types of contract to OCDS's
// mainProcurementCategory, as Find a Tender's opportunities have.
var mainCategories = map[string]string{
"Supplies": "goods",
"Services": "services",
"Works": "works",
}
// UUID returns the UUID of the opportunity for the tender with id.
func UUID(id string) string {
return UUIDPrefix + id
}
// ReleaseID returns the id of the one release of the opportunity for
// tender: its id, as the portal gives each tender one page.
func ReleaseID(tender Tender) string {
return tender.ID
}
// Convert returns the opportunity for each tender, with one release whose
// JSON is the tender as read.
func Convert(tenders []Tender) []*types.Opportunity {
opportunities := make([]*types.Opportunity, 0, len(tenders))
for _, tender := range tenders {
opportunities = append(opportunities, convertOne(tender))
}
return opportunities
}
// convertOne builds the opportunity for one tender.
func convertOne(tender Tender) *types.Opportunity {
published := tender.Published
opportunity := &types.Opportunity{
UUID: UUID(tender.ID),
UUIDType: uuidType,
Title: tender.Title,
Status: "active",
Description: tender.Description,
BuyerName: tender.Buyer,
Classifications: classifications(tender),
MainCategory: mainCategories[tender.ContractType],
MultiLot: tender.Lots > 1,
StartDate: &published,
EndDate: tender.Deadline,
Source: Source,
LatestReleaseDate: tender.Published,
}
release := types.OpportunityRelease{
UUID: opportunity.UUID,
ReleaseID: ReleaseID(tender),
ReleaseDate: tender.Published,
Tags: []types.OpportunityReleaseTag{
{
Tag: releaseTag,
},
},
}
// A Tender is plain data, so marshalling it can't fail.
if encoded, err := json.Marshal(tender); err == nil {
release.JSON = string(encoded)
}
opportunity.Releases = []types.OpportunityRelease{release}
return opportunity
}
// classifications returns the tender's CPV codes as Find a Tender's are
// stored: without the check digit ("48000000", not "48000000-8").
func classifications(tender Tender) []types.ClassificationCode {
codes := make([]types.ClassificationCode, 0, len(tender.CPVCodes))
for _, cpv := range tender.CPVCodes {
code, _, _ := strings.Cut(cpv.Code, "-")
codes = append(codes, types.ClassificationCode{
IsCPV: true,
Code: code,
Classification: cpv.Description,
})
}
return codes
}