Cleaning up tags and url regexes, closes #6
All checks were successful
continuous-integration/drone/push Build is passing

This commit is contained in:
2022-08-03 12:44:04 -04:00
parent d4c4f521ec
commit 0903278f14
4 changed files with 8 additions and 8 deletions

View File

@@ -9,7 +9,7 @@ namespace WebNovelPortalAPI.Scrapers;
public class SyosetuScraper : AbstractScraper
{
protected override string UrlMatchPattern => @"https?:\/\/(\w+)\.syosetu\.com\/\w+\/?";
protected override string UrlMatchPattern => @"https?:\/\/(\w+)\.syosetu\.com\/n\w+";
protected override string BaseUrlPattern => @"https?:\/\/(\w+)\.syosetu\.com";
@@ -35,7 +35,7 @@ public class SyosetuScraper : AbstractScraper
{
string novelInfoBase = $"/novelview/infotop/ncode/";
string novelRegex = @"https?:\/\/\w+\.syosetu\.com\/(\w+)\/?";
string novelCode = new Regex(novelRegex).Match(novelUrl).Groups[1].Value;
string novelCode = new Regex(novelRegex, RegexOptions.IgnoreCase).Match(novelUrl).Groups[1].Value;
string novelInfoPage = $"{baseUrl}{novelInfoBase}{novelCode}";
return await GetPage(novelInfoPage);
@@ -134,8 +134,8 @@ public class SyosetuScraper : AbstractScraper
public override async Task<Novel> ScrapeNovel(string url)
{
var baseUrl = new Regex(BaseUrlPattern).Match(url).Value;
var novelUrl = new Regex(UrlMatchPattern).Match(url).Value;
var baseUrl = new Regex(BaseUrlPattern, RegexOptions.IgnoreCase).Match(url).Value;
var novelUrl = new Regex(UrlMatchPattern, RegexOptions.IgnoreCase).Match(url).Value;
HtmlDocument baseDoc;
HtmlDocument novelInfoPage;
try