1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
|
using System.Security.Cryptography;
using System.Text;
using AngleSharp.Html.Parser;
using I2R.LightNews.Utilities;
namespace I2R.LightNews.Services;
public class GrabberService
{
private readonly ILogger<GrabberService> _logger;
private readonly HttpClient _http;
private const string NrkPrefix = "nrkno";
private const int StaleTime = 100800;
private static AppPath _cachePath => new() {
HostPath = "AppData/__sitecache"
};
public GrabberService(ILogger<GrabberService> logger, HttpClient http) {
_logger = logger;
_http = http;
}
public async Task<NewsArticle> GrabNrkArticleAsync(string url) {
var strippedUrl = url.Replace("https://", "")
.Replace("http://", "")
.Replace("www.", "");
if (!strippedUrl.StartsWith("nrk.no")
|| strippedUrl.StartsWith("nrk.no/mat")
|| strippedUrl.StartsWith("nrk.no/tv")
|| strippedUrl.StartsWith("nrk.no/radio")
|| strippedUrl.StartsWith("nrk.no/xl")
) return default;
using var md5 = MD5.Create();
var articleFilePrefix = "art-" + NrkPrefix + "-" + Convert.ToHexString(md5.ComputeHash(Encoding.UTF8.GetBytes(url)));
var source = await GrabSourceAsync(url, articleFilePrefix, true);
var parser = new HtmlParser();
var doc = await parser.ParseDocumentAsync(source.Content);
var result = new NewsArticle() {
CachedAt = source.CacheFileCreatedAt,
Href = url,
Title = doc.QuerySelector("h1.title")?.TextContent,
Subtitle = doc.QuerySelector(".article-lead p")?.TextContent,
Authors = new List<NewsArticle.Author>()
};
foreach (var authorNode in doc.QuerySelectorAll(".authors .author")) {
var author = new NewsArticle.Author() {
Name = authorNode.QuerySelector(".author__name")?.TextContent,
Title = authorNode.QuerySelector(".author__role")?.TextContent
};
result.Authors.Add(author);
}
DateTime.TryParse(doc.QuerySelector("time.datePublished")?.Attributes["datetime"]?.Value, out var published);
DateTime.TryParse(doc.QuerySelector("time.dateModified")?.Attributes["datetime"]?.Value, out var modified);
result.UpdatedAt = modified;
result.PublishedAt = published;
result.Content = HtmlSanitiser.SanitizeHtmlFragment(doc.QuerySelector(".article-body").InnerHtml, "img,a,.video-reference,.image-reference,.reference");
return result;
}
public async Task<NewsSource> GrabNrkAsync() {
var source = await GrabSourceAsync("https://nrk.no", NrkPrefix);
var parser = new HtmlParser();
var doc = await parser.ParseDocumentAsync(source.Content);
var result = new NewsSource() {
Name = "nrk",
Attribution = "Fra https://nrk.no",
Created = source.CacheFileCreatedAt.DateTime,
CanonicalUrl = doc.QuerySelector("link[rel='canonical']")?.Attributes["href"]?.Value ?? "uvisst",
Articles = new List<NewsArticle>()
};
foreach (var articleAnchorNode in doc.QuerySelectorAll("main section a")) {
var article = new NewsArticle {
Href = articleAnchorNode.Attributes["href"]?.Value.Trim(),
Title = articleAnchorNode.QuerySelector(".kur-room__title span")?.TextContent.Trim()
};
if (
article.Href.IsNullOrWhiteSpace()
|| article.Title.IsNullOrWhiteSpace()
|| (!article.Href?.StartsWith("https://www.nrk.no") ?? true)
|| (article.Href?.StartsWith("https://www.nrk.no/mat") ?? false)
) {
continue;
}
result.Articles.Add(article);
}
return result;
}
private class SourceResult
{
public string CacheFileName { get; set; }
public string Content { get; set; }
public DateTimeOffset CacheFileCreatedAt { get; set; }
}
private async Task<SourceResult> GrabSourceAsync(string url, string prefix, bool forceRefresh = false) {
var cacheFileName = forceRefresh ? default : GetLatestCacheFile(prefix);
if (cacheFileName != default) {
_logger.LogInformation("Returned cached {0} file, filename: {1}", url, cacheFileName.CacheFileName);
cacheFileName.Content = await File.ReadAllTextAsync(_cachePath.GetHostPathForFilename(cacheFileName.CacheFileName));
return cacheFileName;
}
var sourceResponse = await _http.GetAsync(url);
var sourceContent = await sourceResponse.Content.ReadAsStringAsync();
var utcNow = DateTimeOffset.UtcNow;
var newCacheFileName = prefix + "-" + utcNow.ToUnixTimeSeconds() + ".html";
await File.WriteAllTextAsync(_cachePath.GetHostPathForFilename(newCacheFileName), sourceContent);
_logger.LogInformation("Wrote new cache file for {0}, filename: {1}", url, newCacheFileName);
return new SourceResult() {
CacheFileName = newCacheFileName,
CacheFileCreatedAt = utcNow,
Content = sourceContent
};
}
private SourceResult GetLatestCacheFile(string prefix) {
var cacheDirectoryInfo = new DirectoryInfo(_cachePath.HostPath);
if (!cacheDirectoryInfo.Exists) {
cacheDirectoryInfo.Create();
return default;
}
var files = cacheDirectoryInfo.GetFiles();
if (!files.Any()) return default;
var relevantFiles = files.Where(c => c.Name.StartsWith(prefix)).OrderBy(c => c.Name).ToList();
if (!relevantFiles.Any()) return default;
var mostRecentFileName = relevantFiles.Last().Name;
var mostRecentEpochString = new string(mostRecentFileName.Skip(mostRecentFileName.LastIndexOf('-')).Where(Char.IsDigit).ToArray());
long.TryParse(mostRecentEpochString, out var mostRecentEpochLong);
// more than 30 minutes since last grab
if (mostRecentEpochLong + StaleTime < DateTimeOffset.UtcNow.ToUnixTimeSeconds()) return default;
return new SourceResult {
CacheFileName = mostRecentFileName,
CacheFileCreatedAt = DateTimeOffset.FromUnixTimeSeconds(mostRecentEpochLong)
};
}
}
|
