Yevhen Odynets
346369ca11
New scope reading the API instead of scraping HTML: one search path per run, passed raw through --single-uri, and the answer stored as-is into its own SQLite file created from the embedded schema. Command line: --single-uri carries the path after /v1/search/ (category:flac/date:today/page:1) and must name a category; --sleep sets the pause between pages, with the config value as fallback. A day named on the command line is always fetched again and its dump rewritten, so cron can refresh today hourly and yesterday daily. Date placeholders: date:auto walks backwards to the newest day in [srrdb.floor..yesterday] that has no dump yet, closing holes instead of declaring the archive covered. date:today, date:yesterday and date:tomorrow stand for the neighbouring days. Today is never taken by the walk, because a day still being filled would be frozen by its own dump after the first run. Dumps are the cursor as well as the record, so a missing dump directory is an error instead of "nothing harvested yet": a renamed, unmounted or mistyped directory must not send the run silently back to the beginning. An empty day is a normal result and is remembered as harvested; API warnings never are, and they reach the exit code. Writes go through one transaction, so a day lands completely or not at all. group and category come from the release line and the search path; status, nfo, content and synced_at stay NULL. srrdb.log.jsonl records one line per finished run, srrdb.error_log.jsonl keeps failures and API warnings apart by a kind field. Also: the console command contract returns (string, error), so a failing scope reaches the process exit code and cron can tell a failed run from a successful one. config/scope/srrdb.yaml is untracked because its paths differ per host. modernc.org/sqlite replaces the archived libsql client, which only ever talked to a server. pkg/repository/srrdb.go is split by responsibility and covered by table-driven tests.
44 lines
998 B
Go
44 lines
998 B
Go
package handler
|
|
|
|
import (
|
|
"fmt"
|
|
"math"
|
|
"strconv"
|
|
"time"
|
|
|
|
"github.com/spf13/viper"
|
|
|
|
"git.kplus.net.ua/yevhen/resource-scraper/types/constant"
|
|
)
|
|
|
|
func (h *Handler) Prescene() (string, error) {
|
|
currMinute := time.Now().Minute()
|
|
levels := viper.GetInt(constant.CfgKeyLevelsToScrape)
|
|
initPage := strconv.Itoa(currMinute/(60/levels) + 1)
|
|
pagesToScrape := []string{initPage}
|
|
|
|
if levels > 1 {
|
|
var q = (60.0 / 100.0) * (100.0 / float64(levels))
|
|
minute := float64(currMinute + 1)
|
|
|
|
fmt.Printf("FLOAT: %f, %f, %v\n", minute, q, math.Ceil(minute/q))
|
|
|
|
hour := time.Now().Hour() + levels
|
|
|
|
page := hour * int(math.Ceil(minute/q))
|
|
pagesToScrape = append(pagesToScrape, strconv.Itoa(page))
|
|
}
|
|
|
|
if _, err := h.services.Prescene.GetSrrDb(); err != nil {
|
|
return "ps", fmt.Errorf("getting srr db: %w", err)
|
|
}
|
|
|
|
if _, err := h.services.Prescene.GetPage(pagesToScrape); err != nil {
|
|
return "ps", fmt.Errorf("getting page: %w", err)
|
|
}
|
|
|
|
fmt.Printf("%+v\n", pagesToScrape)
|
|
|
|
return "ps", nil
|
|
}
|