这是indexloc提供的服务，不要输入任何密码
Skip to content

CommonCrawl dynamic year range #687

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 1, 2022
Merged

CommonCrawl dynamic year range #687

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions v2/pkg/subscraping/sources/commoncrawl/commoncrawl.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,14 +6,21 @@ import (
"context"
"fmt"
"net/url"
"strconv"
"strings"
"time"

jsoniter "github.com/json-iterator/go"

"github.com/projectdiscovery/subfinder/v2/pkg/subscraping"
)

const indexURL = "https://index.commoncrawl.org/collinfo.json"
const (
indexURL = "https://index.commoncrawl.org/collinfo.json"
maxYearsBack = 5
)

var year = time.Now().Year()

type indexResponse struct {
ID string `json:"id"`
Expand All @@ -23,8 +30,6 @@ type indexResponse struct {
// Source is the passive scraping agent
type Source struct{}

var years = [...]string{"2020", "2019", "2018", "2017"}

// Run function returns all subdomains found with the service
func (s *Source) Run(ctx context.Context, domain string, session *subscraping.Session) <-chan subscraping.Result {
results := make(chan subscraping.Result)
Expand All @@ -48,6 +53,11 @@ func (s *Source) Run(ctx context.Context, domain string, session *subscraping.Se
}
resp.Body.Close()

years := make([]string, 0)
for i := 0; i < maxYearsBack; i++ {
years = append(years, strconv.Itoa(year-i))
}

searchIndexes := make(map[string]string)
for _, year := range years {
for _, index := range indexes {
Expand Down