I'm trying to parse the timetable content using goquery to work with it later. But I have a problem.
I have two functions. The first one takes an html document and searches for a token (csrfmiddlewaretoken) and the second one sends a request using this token and extracts information. Finishing extracting all necessary information from the page, I search for the token to use it in future request and store it.
But for some reason found token turns into an empty string when it reaches if len(foundCsrfToken) == 0 {
. If I print length of the token just before the statement it prints this:
...
64
0
...
I've got rid of all goroutines in case if it's the problem.
func findCsrfMiddlewareToken(responseBody io.Reader) (string, error) {
document, err := goquery.NewDocumentFromReader(responseBody)
if err != nil {
return "", err
}
var foundCsrfToken string
document.Find("script").Each(func(_ int, scrpt *goquery.Selection) {
scriptText := scrpt.Text()
if funcDefIndex := strings.Index(scriptText, "function Filter"); funcDefIndex != -1 {
csrfTokenValueStart := strings.Index(scriptText, "csrfmiddlewaretoken: '")
offset := csrfTokenValueStart + len("csrfmiddlewaretoken: '")
foundCsrfToken = scriptText[offset : offset+csrfMiddlewareTokenLength]
}
})
if len(foundCsrfToken) == 0 {
return "", errNoCsrfMiddlewareToken
}
return foundCsrfToken, nil
}
func (parser *TimetableParser) ParseTimetable(timetableFilterInfo internal.TimetableInfo) (internal.Timetable, error) {
timetable := internal.Timetable{}
requestBody := makeFormValues(timetableFilterInfo, parser.csrfMiddlewareToken).Encode()
request, err := http.NewRequest("POST", baseUrl, strings.NewReader(requestBody))
if err != nil {
return timetable, err
}
request.Header.Add("Content-Type", "application/x-www-form-urlencoded")
request.Header.Add("Content-Length", strconv.Itoa(len(requestBody)))
request.Header.Add("Referer", baseUrl)
response, err := parser.client.Do(request)
if err != nil {
return timetable, err
}
defer response.Body.Close()
document, err := goquery.NewDocumentFromReader(response.Body)
if err != nil {
return timetable, err
}
document.Find("table#schedule").Find("tr").Each(func(rowIndex int, row *goquery.Selection) {
subjectTimeElement := row.Closest("td")
subjectTimeElement.NextAll().Each(func(columnIndex int, cell *goquery.Selection) {
subjectInfo := extractSubjectInfoFromCell(cell)
subjectInfo.Order = rowIndex
timetable.Subjects[columnIndex][rowIndex] = subjectInfo
})
})
parser.csrfMiddlewareToken, err = findCsrfMiddlewareToken(response.Body)
if err != nil {
log.Println("csrfMiddlewareToken: " + err.Error())
}
return timetable, nil
}
Go version: go1.17.1 windows/amd64
goquery version: 1.7.1