diff options
| author | Serguey Parkhomovsky <xindigo@gmail.com> | 2025-12-25 22:14:43 -0800 |
|---|---|---|
| committer | Serguey Parkhomovsky <xindigo@gmail.com> | 2025-12-25 22:21:49 -0800 |
| commit | 38977b259a46b60f0ba9a223a0c9ee4e908facd9 (patch) | |
| tree | c0dd61978b9aac2a873c00ede6da4028665f750e | |
| parent | 7446cb7120afa221070ac996cf327e0bea1f9ff7 (diff) | |
add artist scraping capability
| -rw-r--r-- | go.mod | 6 | ||||
| -rw-r--r-- | go.sum | 71 | ||||
| -rw-r--r-- | main.go | 108 |
3 files changed, 175 insertions, 10 deletions
@@ -3,3 +3,9 @@ module weeklybeats-scraper go 1.25.1 require github.com/mattn/go-sqlite3 v1.14.32 + +require ( + github.com/PuerkitoBio/goquery v1.11.0 // indirect + github.com/andybalholm/cascadia v1.3.3 // indirect + golang.org/x/net v0.47.0 // indirect +) @@ -1,2 +1,73 @@ +github.com/PuerkitoBio/goquery v1.11.0 h1:jZ7pwMQXIITcUXNH83LLk+txlaEy6NVOfTuP43xxfqw= +github.com/PuerkitoBio/goquery v1.11.0/go.mod h1:wQHgxUOU3JGuj3oD/QFfxUdlzW6xPHfqyHre6VMY4DQ= +github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM= +github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA= +github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs= github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y= +github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= +golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc= +golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU= +golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8= +golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk= +golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= +golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= +golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= +golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= +golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= +golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= +golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg= +golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk= +golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44= +golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= +golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4= +golang.org/x/net v0.47.0 h1:Mx+4dIFzqraBXUugkia1OOvlD6LemFo1ALMHjrXDOhY= +golang.org/x/net v0.47.0/go.mod h1:/jNxtkgq5yWUGYkaZGqo27cfGZ1c5Nen03aYrrKpVRU= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y= +golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= +golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo= +golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU= +golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk= +golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY= +golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM= +golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= +golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8= +golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE= +golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= +golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= +golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= +golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= +golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= +golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58= +golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= @@ -7,13 +7,22 @@ import ( "io" "log" "net/http" + "net/url" "strconv" "strings" "time" + "github.com/PuerkitoBio/goquery" _ "github.com/mattn/go-sqlite3" ) +const ( + artistFetchDelay = 250 * time.Millisecond + pageFetchDelay = 500 * time.Millisecond + maxPages = 1000 + itemsPerPage = 1000 +) + // RSS structures type RSS struct { XMLName xml.Name `xml:"rss"` @@ -48,6 +57,44 @@ type TitleAuthor struct { Author string } +func extractUsername(trackURL string) (string, error) { + u, err := url.Parse(trackURL) + if err != nil { + return "", err + } + + parts := strings.Split(strings.Trim(u.Path, "/"), "/") + if len(parts) < 1 { + return "", fmt.Errorf("invalid URL format: %s", trackURL) + } + + return parts[0], nil +} + +func fetchArtistName(trackURL string) (string, error) { + resp, err := http.Get(trackURL) + if err != nil { + return "", err + } + defer resp.Body.Close() + + if resp.StatusCode != 200 { + return "", fmt.Errorf("HTTP %d", resp.StatusCode) + } + + doc, err := goquery.NewDocumentFromReader(resp.Body) + if err != nil { + return "", err + } + + artistName := strings.TrimSpace(strings.TrimPrefix(doc.Find("#item_user a").Text(), "By ")) + if artistName == "" { + return "", fmt.Errorf("artist name not found") + } + + return artistName, nil +} + func parseYearWeek(date string) (YearWeek, error) { parts := strings.Split(date, "/") if len(parts) != 2 { @@ -94,7 +141,7 @@ func isValidXMLByte(b byte) bool { } func fetchRSSPage(year, page int) (*RSS, error) { - url := fmt.Sprintf("https://weeklybeats.com/music/rss?limit=1000&year=%d&page=%d", year, page) + url := fmt.Sprintf("https://weeklybeats.com/music/rss?limit=%d&year=%d&page=%d", itemsPerPage, year, page) resp, err := http.Get(url) if err != nil { @@ -122,9 +169,49 @@ func fetchRSSPage(year, page int) (*RSS, error) { return &rss, nil } -func insertItems(insertStmt *sql.Stmt, items []Item) int { +func getArtistNameFromTitle(title string) (string, error) { + titleAuthor, err := parseTitle(title) + if err != nil { + return "", err + } + return titleAuthor.Author, nil +} + +func resolveArtistName(item Item, cache map[string]string) (string, error) { + username, err := extractUsername(item.Link) + if err != nil { + log.Printf("Failed to extract username from '%s': %v", item.Link, err) + return getArtistNameFromTitle(item.Title) + } + + // Try cache first + if artistName := cache[username]; artistName != "" { + return artistName, nil + } + + // Not in cache, fetch from track page + artistName, err := fetchArtistName(item.Link) + if err != nil { + log.Printf("Failed to fetch artist for '%s': %v, using RSS fallback", username, err) + return getArtistNameFromTitle(item.Title) + } + + cache[username] = artistName + fmt.Printf("Cached artist name '%s' for username '%s'\n", artistName, username) + time.Sleep(artistFetchDelay) + + return artistName, nil +} + +func insertItems(insertStmt *sql.Stmt, items []Item, cache map[string]string) int { inserted := 0 for _, item := range items { + artistName, err := resolveArtistName(item, cache) + if err != nil { + log.Printf("Failed to resolve artist for item '%s': %v", item.Title, err) + continue + } + titleAuthor, err := parseTitle(item.Title) if err != nil { log.Printf("Failed to parse title for item '%s': %v", item.Title, err) @@ -137,7 +224,7 @@ func insertItems(insertStmt *sql.Stmt, items []Item) int { continue } - _, err = insertStmt.Exec(titleAuthor.Title, item.Link, titleAuthor.Author, yearWeek.Week, yearWeek.Year, item.Enclosure.URL) + _, err = insertStmt.Exec(titleAuthor.Title, item.Link, artistName, yearWeek.Week, yearWeek.Year, item.Enclosure.URL) if err != nil { log.Printf("Failed to insert item '%s': %v", item.Title, err) continue @@ -147,7 +234,7 @@ func insertItems(insertStmt *sql.Stmt, items []Item) int { return inserted } -func scrapeYear(year int, insertStmt *sql.Stmt) int { +func scrapeYear(year int, insertStmt *sql.Stmt, cache map[string]string) int { totalItems := 0 page := 1 @@ -167,16 +254,15 @@ func scrapeYear(year int, insertStmt *sql.Stmt) int { fmt.Printf("Found %d items on page %d\n", len(rss.Channel.Items), page) - pageItems := insertItems(insertStmt, rss.Channel.Items) + pageItems := insertItems(insertStmt, rss.Channel.Items, cache) fmt.Printf("Inserted %d new items from page %d\n", pageItems, page) totalItems += pageItems - time.Sleep(500 * time.Millisecond) - + time.Sleep(pageFetchDelay) page++ - if page > 1000 { - fmt.Println("Reached maximum page limit (1000), stopping") + if page > maxPages { + fmt.Printf("Reached maximum page limit (%d), stopping\n", maxPages) break } } @@ -249,9 +335,11 @@ func main() { } defer insertStmt.Close() + cache := make(map[string]string) + totalItems := 0 for year := 2012; year <= 2024; year += 2 { - totalItems += scrapeYear(year, insertStmt) + totalItems += scrapeYear(year, insertStmt, cache) } fmt.Printf("\nScraping complete! Total items processed: %d\n", totalItems) |
