Kratika/Gaurav: initial pass

cmd/nse_downloader/main.go

@@ -16,6 +16,11 @@ import (
 	"codermana.com/go/pkg/value_analysis/pkg/unzipper"
 )
 
+// TODOs
+// 1. Download not only Nifty50 but as much as possible
+// 2. Download quarterly statements as well as annual statements
+// 3. Build a similar tool for BSE
+
 func init() {
 	log.SetLevel(log.DebugLevel)
 	log.SetReportCaller(true)

cmd/process_statements/main.go

@@ -0,0 +1,51 @@
+package main
+
+import (
+	"fmt"
+
+	"github.com/dslipak/pdf"
+)
+
+// TODOs
+// 1. Figure out which file actually contains the statement (-0 vs -1)
+// Approach:
+// 2. Figure out if the year matches the statement title
+// 3. Extract the following data from the pdfs
+// - financial
+// - management
+// - text and tidbits (sentiment analysis)
+// 4. Build intelligence through analysis of past data & news reports & any other source
+
+func main() {
+	// pdf.DebugOn = true
+	content, err := readPdf("./statements/ASIANPAINT/2022-2023.pdf") // Read local pdf file
+	if err != nil {
+		panic(err)
+	}
+	fmt.Println(content)
+	return
+}
+
+func readPdf(path string) (string, error) {
+	r, err := pdf.Open(path)
+	if err != nil {
+		return "", err
+	}
+	totalPage := r.NumPage()
+
+	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
+		p := r.Page(pageIndex)
+		if p.V.IsNull() {
+			continue
+		}
+
+		rows, _ := p.GetTextByRow()
+		for _, row := range rows {
+			println(">>>> row: ", row.Position)
+			for _, word := range row.Content {
+				fmt.Println(word.S)
+			}
+		}
+	}
+	return "", nil
+}

go.mod

@@ -4,4 +4,7 @@ go 1.21.6
 
 require github.com/sirupsen/logrus v1.9.3
 
-require golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8 // indirect
+require (
+	github.com/dslipak/pdf v0.0.2 // indirect
+	golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8 // indirect
+)

go.sum

@@ -1,6 +1,8 @@
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dslipak/pdf v0.0.2 h1:djAvcM5neg9Ush+zR6QXB+VMJzR6TdnX766HPIg1JmI=
+github.com/dslipak/pdf v0.0.2/go.mod h1:2L3SnkI9cQwnAS9gfPz2iUoLC0rUZwbucpbKi5R1mUo=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=