mirror of
https://github.com/hashiromer/Upwork-Jobs-scraper-.git
synced 2025-12-29 16:16:01 +00:00
Added types for upwork api respone
This commit is contained in:
@@ -2,21 +2,21 @@ package upwork
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
)
|
||||
|
||||
type UpworkPipeLine struct {
|
||||
upworkClient *Upwork
|
||||
iterations int
|
||||
// queue := []int{}
|
||||
filepaths []string
|
||||
}
|
||||
|
||||
func InitPipeline() *UpworkPipeLine {
|
||||
u := UpworkPipeLine{
|
||||
upworkClient: InitUpwork(),
|
||||
iterations: 32,
|
||||
}
|
||||
return &u
|
||||
}
|
||||
@@ -24,12 +24,12 @@ func InitPipeline() *UpworkPipeLine {
|
||||
func (u *UpworkPipeLine) CombineFiles() error {
|
||||
|
||||
var all_jobs []interface{}
|
||||
all_filenames, err := filepath.Glob("data/*.json")
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
// all_filenames, err := filepath.Glob("data/*.json")
|
||||
// if err != nil {
|
||||
// panic(err)
|
||||
// }
|
||||
|
||||
for _, file := range all_filenames {
|
||||
for _, file := range u.filepaths {
|
||||
data, err := os.ReadFile(file)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
@@ -83,11 +83,15 @@ func isJSON(s string) bool {
|
||||
}
|
||||
|
||||
func isApiError(data string) bool {
|
||||
|
||||
var result map[string]interface{}
|
||||
|
||||
//Parse data as json
|
||||
err := json.Unmarshal([]byte(data), &result)
|
||||
if err != nil {
|
||||
log.Print("The Api did not return expected response")
|
||||
log.Print("The following was the response from API")
|
||||
log.Print(data)
|
||||
panic(err)
|
||||
}
|
||||
|
||||
@@ -106,6 +110,32 @@ func (u *UpworkPipeLine) validateResponse(data string) bool {
|
||||
|
||||
}
|
||||
|
||||
func (u *UpworkPipeLine) getTotalDocuments(urlArgs UrlArgs) (int, error) {
|
||||
client := u.upworkClient
|
||||
url := client.ConstructUrl(urlArgs)
|
||||
resp, err := u.upworkClient.SendRequest(url)
|
||||
|
||||
if err != nil {
|
||||
|
||||
log.Fatal(err)
|
||||
return 0, err
|
||||
}
|
||||
|
||||
// check if response is valid
|
||||
if !u.validateResponse(resp) {
|
||||
return 0, fmt.Errorf("invalid response")
|
||||
}
|
||||
|
||||
var API_Response UpworkApiResponse
|
||||
|
||||
json.Unmarshal([]byte(resp), &API_Response)
|
||||
|
||||
total_docs := API_Response.SearchResults.Paging.Total
|
||||
s := fmt.Sprintf("totalzz is %d", total_docs)
|
||||
log.Print(s)
|
||||
return total_docs, nil
|
||||
}
|
||||
|
||||
func (u *UpworkPipeLine) handleRequest(urlArgs UrlArgs, iteration int) {
|
||||
client := u.upworkClient
|
||||
url := client.ConstructUrl(urlArgs)
|
||||
@@ -120,7 +150,12 @@ func (u *UpworkPipeLine) handleRequest(urlArgs UrlArgs, iteration int) {
|
||||
err = u.saveToFile([]byte(resp), filename)
|
||||
if err != nil {
|
||||
log.Println(err)
|
||||
panic(errors.New("could not save file"))
|
||||
} else {
|
||||
u.filepaths = append(u.filepaths, filename)
|
||||
|
||||
}
|
||||
|
||||
} else {
|
||||
log.Println("Invalid response returned")
|
||||
|
||||
@@ -140,27 +175,64 @@ func (u *UpworkPipeLine) Run(query string) error {
|
||||
}
|
||||
|
||||
var iteration int
|
||||
for iteration = 1; iteration <= u.iterations; iteration++ {
|
||||
log.Println("Iteration: ", iteration)
|
||||
var perPage int
|
||||
var total_docs int
|
||||
|
||||
info_message := fmt.Sprintf("Finding Total Jobs for %s", query)
|
||||
fmt.Println(info_message)
|
||||
|
||||
urlArgs := UrlArgs{
|
||||
Page: 1,
|
||||
Per_Page: 10,
|
||||
Query: query,
|
||||
}
|
||||
|
||||
//Find total number of iterations
|
||||
perPage = 50
|
||||
total_docs, err = u.getTotalDocuments(urlArgs)
|
||||
|
||||
log.Print(total_docs)
|
||||
if err == nil {
|
||||
info_message := fmt.Sprintf("%s has a total of %d jobs", query, total_docs)
|
||||
fmt.Println(info_message)
|
||||
iteration = total_docs / perPage
|
||||
|
||||
if iteration >= 100 {
|
||||
iteration = 100
|
||||
}
|
||||
|
||||
info_message = fmt.Sprintf("A total of %d iterations will be performed", iteration)
|
||||
fmt.Println(info_message)
|
||||
|
||||
//Found total iterations
|
||||
u.handledataIteration(perPage, iteration, query)
|
||||
err = u.CombineFiles()
|
||||
os.RemoveAll("data")
|
||||
|
||||
if err != nil {
|
||||
panic(err)
|
||||
|
||||
}
|
||||
|
||||
return nil
|
||||
|
||||
} else {
|
||||
log.Fatal("Could not retrive total number of jobs")
|
||||
panic(err)
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
func (u *UpworkPipeLine) handledataIteration(p_per int, iters int, query string) {
|
||||
for index := 1; index <= iters; index++ {
|
||||
log.Println("Iteration: ", index)
|
||||
urlArgs := UrlArgs{
|
||||
Page: iteration,
|
||||
Page: index,
|
||||
Per_Page: 50,
|
||||
Query: query,
|
||||
}
|
||||
//It is possible to use a go routine here but be nice to the api or you will be rate limited pretty quickly. It is technically possible to circumvent it using a proxy but it is not recommended.
|
||||
// go u.handleRequest(urlArgs, i)
|
||||
u.handleRequest(urlArgs, iteration)
|
||||
|
||||
u.handleRequest(urlArgs, index)
|
||||
|
||||
}
|
||||
|
||||
err = u.CombineFiles()
|
||||
os.RemoveAll("data")
|
||||
|
||||
if err != nil {
|
||||
panic(err)
|
||||
|
||||
}
|
||||
|
||||
return nil
|
||||
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user