2 Commits
Author SHA1 Message Date
jim bc9985a6f0 Add support for fetching and storing reply text
- Add database migration and update logic for replyText column in Notes
- Implement batch collection of missing reply text via Tumblr API
- Add new API integration to fetch reply text for replies
- Enhance DataAccess with methods to query/update replyText
- Update CLI: -replies now collects and stores reply text
- Improve logging (archive logs/), error handling, and output
- Remove TL.db from source control
2026-02-12 23:12:54 -06:00
jim 0e5fb124a0 Enhance filtering, SQL, and error handling logic
- Added `beforeDate` parameter to filter posts by `NotesGatheredDateTime`.
- Improved SQL queries with additional joins and conditions.
- Refactored exception handling for better resource cleanup.
- Enhanced string comparisons to support case-insensitivity.
- Added `GetReplies` method for fetching replies.
- Improved handling of `ReblogRecord` data and filtering logic.
- Updated `-collect` command to support optional date filtering.
- Adjusted `launchSettings.json` for testing with specific parameters.
- Improved logging and error reporting in API and database operations.
2025-12-11 23:19:19 -06:00
6 changed files with 770 additions and 304 deletions
+24 -19
View File
@@ -1,19 +1,24 @@
<?xml version="1.0" encoding="UTF-8"?><sqlb_project><db path="D:/NextCloud/C#/URLNotesGrabberCORE/URLNotesGrabberCORE/bin/Debug/net8.0/TL.db" readonly="1" foreign_keys="1" case_sensitive_like="0" temp_store="0" wal_autocheckpoint="1000" synchronous="2"/><attached/><window><main_tabs open="structure browser pragmas query" current="3"/></window><tab_structure><column_width id="0" width="300"/><column_width id="1" width="0"/><column_width id="2" width="100"/><column_width id="3" width="3571"/><column_width id="4" width="0"/><expanded_item id="0" parent="1"/><expanded_item id="1" parent="1"/><expanded_item id="2" parent="1"/><expanded_item id="3" parent="1"/></tab_structure><tab_browse><table title="Blogs" custom_title="0" dock_id="1" table="4,5:mainBlogs"/><dock_state state="000000ff00000000fd0000000100000002000005f40000031dfc0100000001fb000000160064006f0063006b00420072006f00770073006500310100000000000005f4000000fb00ffffff000002130000000000000004000000040000000800000008fc00000000"/><default_encoding codec=""/><browse_table_settings><table schema="main" name="Blogs" show_row_id="0" encoding="" plot_x_axis="" unlock_view_pk="_rowid_" freeze_columns="0"><sort><column index="0" mode="1"/></sort><column_widths><column index="1" value="257"/><column index="2" value="48"/></column_widths><filter_values/><conditional_formats/><row_id_formats/><display_formats/><hidden_columns/><plot_y_axes/><global_filter/></table></browse_table_settings></tab_browse><tab_sql><sql name="SQL 1*">SELECT
BlogName || '.tumblr.com/post/' || postID,
datetime(NotesGatheredDateTime, 'unixepoch'), *
FROM
Posts
WHERE
NotesGatheredDateTime &lt;&gt; 0
ORDER BY
postdate desc</sql><sql name="SQL 2*">SELECT
datetime(TimeStamp, 'unixepoch'),
RootBlogName || '.tumblr.com/post/' || postid,
*,
NoteBlogName || '.tumblr.com'
FROM
Notes␍
WHERE RootBlogName NOT IN ('xlittle-ghost', 'glimmerin-darlin')
ORDER BY␍
TimeStamp desc</sql><current_tab id="0"/></tab_sql></sqlb_project>
<?xml version="1.0" encoding="UTF-8"?><sqlb_project><db path="" readonly="1" foreign_keys="" case_sensitive_like="" temp_store="" wal_autocheckpoint="" synchronous=""/><attached/><window><main_tabs open="structure browser pragmas query" current="3"/></window><tab_structure><column_width id="0" width="300"/><column_width id="1" width="0"/><column_width id="2" width="100"/><column_width id="3" width="3571"/><column_width id="4" width="0"/></tab_structure><tab_browse><table title="." custom_title="0" dock_id="4" table="0,0:"/><dock_state state="000000ff00000000fd0000000100000002000005f40000030ffc0100000002fb000000160064006f0063006b00420072006f00770073006500310100000000000005f40000000000000000fb000000160064006f0063006b00420072006f00770073006500340100000000ffffffff0000011700ffffff000005f40000000000000004000000040000000800000008fc00000000"/><default_encoding codec=""/><browse_table_settings/></tab_browse><tab_sql><sql name="SQL 1">SELECT
BlogName || '.tumblr.com/post/' || postID,
datetime(NotesGatheredDateTime, 'unixepoch'), *
FROM
Posts
WHERE
NotesGatheredDateTime &lt;&gt; 0
ORDER BY
postdate desc</sql><sql name="SQL 2*">SELECT
datetime(TimeStamp, 'unixepoch'),
RootBlogName || '.tumblr.com/post/' || N.postid,
*,
NoteBlogName || '.tumblr.com'
FROM
Notes N
inner JOIN
Posts P on P.PostID = N.PostID and P.BlogName = N.RootBlogName
WHERE RootBlogName NOT IN ('xlittle-ghost', 'glimmerin-darlin', 'vvenus-child')␍
and type like 'r%'␍
and RootBlogName = 'zomb-eh'␍
and P.HasImage = 1
ORDER BY
TimeStamp desc</sql><current_tab id="1"/></tab_sql></sqlb_project>
+378 -65
View File
@@ -81,6 +81,57 @@ namespace URLNotesGrabberCORE
return dateTime;
}
public static void EnsureReplyTextColumnExists(string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
try
{
connection.Open();
// Check if replyText column exists
string checkSql = "PRAGMA table_info(Notes);";
using (SQLiteCommand command = new SQLiteCommand(checkSql, connection))
{
using (SQLiteDataReader reader = command.ExecuteReader())
{
bool columnExists = false;
while (reader.Read())
{
string columnName = reader.GetString(1);
if (columnName.Equals("replyText", StringComparison.OrdinalIgnoreCase))
{
columnExists = true;
break;
}
}
if (!columnExists)
{
// Add the column if it doesn't exist
connection.Close();
connection.Open();
string addColumnSql = "ALTER TABLE Notes ADD COLUMN replyText TEXT DEFAULT '.';";
using (SQLiteCommand addCommand = new SQLiteCommand(addColumnSql, connection))
{
addCommand.ExecuteNonQuery();
Console.WriteLine("[Migration] Added replyText column to Notes table");
}
}
}
}
}
catch (Exception ex)
{
Console.WriteLine($"Error checking/creating replyText column: {ex.Message}");
}
finally
{
connection.Close();
}
}
#region Adds
public static void AddBlog(string blogName, string DBPath = @"TL.db")
{
@@ -93,10 +144,14 @@ namespace URLNotesGrabberCORE
{
connection.Open();
string sql = "INSERT OR IGNORE INTO Blogs (BlogName) values('" + blogName + "')";
SQLiteCommand command = new SQLiteCommand(sql, connection);
command.ExecuteNonQuery();
// Insert BlogName and DateAdded (current UTC datetime)
string sql = "INSERT OR IGNORE INTO Blogs (BlogName, DateAdded) VALUES (@BlogName, @DateAdded)";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@BlogName", blogName);
command.Parameters.AddWithValue("@DateAdded", DateTime.Now.ToString("yyyy-MM-dd HH:mm:ss"));
command.ExecuteNonQuery();
}
// Console.WriteLine("+ " + blogName);
}
catch (Exception ex)
@@ -145,7 +200,7 @@ namespace URLNotesGrabberCORE
Title,
HasImage
) VALUES (" +
Q(blogName) + ", " + postID +", " + Q(reblogURL) + ", " + Q(postDate) + ", " + Q(postURL) + ", " + Q(slug) + ", " + Q(reblogKey) + ", " + Q(reblogName) + ", " + Q(summary) + ", " + Q(quote) + ", " + Q(body) + ", " + Q(tags) + ", " + Q(link) + ", " + Q(photoURL) + ", " + Q(photoCaption) + ", " + Q(downloadedFiles) + ", " + Q(audioCaption) + ", " + Q(question) + ", " + Q(answer) + ", " + Q(title) + ", " + hasImage + ")";
Q(blogName) + ", " + postID + ", " + Q(reblogURL) + ", " + Q(postDate) + ", " + Q(postURL) + ", " + Q(slug) + ", " + Q(reblogKey) + ", " + Q(reblogName) + ", " + Q(summary) + ", " + Q(quote) + ", " + Q(body) + ", " + Q(tags) + ", " + Q(link) + ", " + Q(photoURL) + ", " + Q(photoCaption) + ", " + Q(downloadedFiles) + ", " + Q(audioCaption) + ", " + Q(question) + ", " + Q(answer) + ", " + Q(title) + ", " + hasImage + ")";
SQLiteCommand command = new SQLiteCommand(sql, connection);
command.ExecuteNonQuery();
@@ -156,27 +211,27 @@ namespace URLNotesGrabberCORE
{
Console.WriteLine(ex.Message);
///
try
{
connection.Open();
try
{
connection.Open();
string sql = "UPDATE Posts SET hasImage = " + hasImage + "WHERE blogName = '" + blogName + "' AND postID = '" + postID + "'";
SQLiteCommand command = new SQLiteCommand(sql, connection);
string sql = "UPDATE Posts SET hasImage = " + hasImage + "WHERE blogName = '" + blogName + "' AND postID = '" + postID + "'";
SQLiteCommand command = new SQLiteCommand(sql, connection);
command.ExecuteNonQuery();
}
catch (Exception ex2)
command.ExecuteNonQuery();
}
catch (Exception ex2)
{
if (ex2.Message != "constraint failed\r\nUNIQUE constraint failed: Posts.BlogName, Posts.PostID")
{
if (ex2.Message != "constraint failed\r\nUNIQUE constraint failed: Posts.BlogName, Posts.PostID")
{
Console.WriteLine(ex2.Message);
}
Console.WriteLine(ex2.Message);
}
finally
{
connection.Close();
}
///
}
finally
{
connection.Close();
}
///
}
}
finally
@@ -188,7 +243,7 @@ namespace URLNotesGrabberCORE
public static void AddAPICount(string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
try
{
@@ -226,7 +281,7 @@ namespace URLNotesGrabberCORE
{
connection.Open();
string sql = "INSERT OR IGNORE INTO Notes (rootBlogName, noteBlogName, PostID, TimeStamp, Type) values(@rootBlogName, @noteBlogName, @PostID, @TimeStamp, @Type)";
string sql = "INSERT OR IGNORE INTO Notes (rootBlogName, noteBlogName, PostID, TimeStamp, Type, DatetimeCrawled) values(@rootBlogName, @noteBlogName, @PostID, @TimeStamp, @Type, @DatetimeCrawled)";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@rootBlogName", rootBlogName);
@@ -234,6 +289,7 @@ namespace URLNotesGrabberCORE
command.Parameters.AddWithValue("@PostID", postID);
command.Parameters.AddWithValue("@TimeStamp", timestamp);
command.Parameters.AddWithValue("@Type", type ?? string.Empty);
command.Parameters.AddWithValue("@DatetimeCrawled", DateTime.Now.ToString("yyyy-MM-dd HH:mm:ss"));
command.ExecuteNonQuery();
}
@@ -243,7 +299,7 @@ namespace URLNotesGrabberCORE
if (ex.Message != "constraint failed\r\nUNIQUE constraint failed: Notes.RootBlogName, Notes.PostID, Notes.TimeStamp, Notes.Type, Notes.NoteBlogName")
{
Console.WriteLine(ex.Message);
Console.WriteLine("^^^^^ - SHORTCUT");
Console.WriteLine("^^^^^ - SHORTCUT");
}
}
finally
@@ -262,7 +318,7 @@ namespace URLNotesGrabberCORE
/// <param name="withoutNotesOnly"></param>
/// <param name="DBPath"></param>
/// <returns>blogName, postID, lastNoteTimestamp, notesGatheredTimestamp</returns>
public static List<Tuple<string, long, long, long>> GetPosts(bool withoutNotesOnly = false, string DBPath = @"TL.db")
public static List<Tuple<string, long, long, long>> GetPosts(bool withoutNotesOnly = false, DateTime? beforeDate = null, string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
List<Tuple<string, long, long, long>> posts = new List<Tuple<string, long, long, long>>();
@@ -271,32 +327,39 @@ namespace URLNotesGrabberCORE
{
connection.Open();
string sql = "SELECT " +
" Posts.BlogName, " + Environment.NewLine +
string sql = "SELECT " +
" MAX(Posts.BlogName) as BlogName, " + Environment.NewLine +
" Posts.PostID, " + Environment.NewLine +
" Max(IFNULL(Notes.timestamp, 1925013599)) as LatestNoteTimestamp, " + Environment.NewLine +
" 1925013599 as LatestNoteTimestamp, " + Environment.NewLine +
" Posts.NotesGatheredDatetime, " + Environment.NewLine +
" CNT.CNT " + Environment.NewLine +
"FROM " + Environment.NewLine +
" Posts " + Environment.NewLine +
" LEFT OUTER JOIN " + Environment.NewLine +
" LEFT OUTER JOIN " + Environment.NewLine +
" Notes ON Notes.RootBlogName = Posts.BlogName AND Notes.PostID = Posts.PostID " + Environment.NewLine +
" LEFT OUTER JOIN " + Environment.NewLine +
" ( select BlogName, count(PostID) as CNT from Posts group by BlogName) CNT on CNT.blogName = Posts.BlogName " +
"WHERE NotFound = 0 " + Environment.NewLine;
"WHERE NotFound = 0 AND HasImage = 1 AND DownloadedFiles <> '.' " + Environment.NewLine;
if (withoutNotesOnly)
sql += " and HasNotesGathered = 0 " + Environment.NewLine ;
sql += "GROUP BY " + Environment.NewLine +
sql += " and HasNotesGathered = 0 " + Environment.NewLine;
// Filter by NotesGatheredDateTime if beforeDate is provided
if (beforeDate.HasValue)
{
long unixTimestamp = new DateTimeOffset(beforeDate.Value).ToUnixTimeSeconds();
sql += $" AND (NotesGatheredDateTime < {unixTimestamp} OR NotesGatheredDateTime IS NULL) " + Environment.NewLine;
}
sql += "GROUP BY " + Environment.NewLine +
" Posts.BlogName, Posts.PostID " + Environment.NewLine +
"ORDER BY " + Environment.NewLine +
" notesgathereddatetime, Posts.PostDate DESC, Posts.BlogName, Posts.PostID" + Environment.NewLine;
" notesgathereddatetime, Posts.PostDate desc, Posts.BlogName, Posts.PostID" + Environment.NewLine;
Console.WriteLine(withoutNotesOnly);
Console.WriteLine(sql);
Console.Write(">"); //Console.ReadKey();
// Thread.Sleep(1000);
//Console.WriteLine(withoutNotesOnly);
//Console.WriteLine(sql);
//Console.Write(">"); //Console.ReadKey();
//Thread.Sleep(250);
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
@@ -332,7 +395,7 @@ namespace URLNotesGrabberCORE
}
return posts;
}
public static List<Tuple<string, long>> GetReplies(string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
@@ -375,6 +438,107 @@ namespace URLNotesGrabberCORE
return posts;
}
public static List<Tuple<string, long>> GetRepliesWithMissingText(string DBPath = @"TL.db", int limit = 50)
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
List<Tuple<string, long>> posts = new List<Tuple<string, long>>();
try
{
connection.Open();
string sql = @"SELECT DISTINCT Notes.RootBlogName as blogName, Notes.PostID,
MAX(Notes.timestamp) as LatestTimestamp
FROM Notes
WHERE Notes.type = 'reply'
AND (Notes.replyText IS NULL OR Notes.replyText = '' OR Notes.replyText = '.')
GROUP BY Notes.RootBlogName, Notes.PostID
ORDER BY LatestTimestamp ASC
LIMIT @limit";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@limit", limit);
using (SQLiteDataReader reader = command.ExecuteReader())
{
while (reader.Read())
{
Tuple<string, long> post = default;
string blog = null;
long id = 0;
blog = reader.GetString(reader.GetOrdinal("blogName"));
id = reader.GetInt64(reader.GetOrdinal("PostID"));
post = new Tuple<string, long>(blog, id);
posts.Add(post);
}
}
}
}
catch (Exception ex)
{
Console.WriteLine($"Error getting replies with missing text: {ex.Message}");
}
finally
{
connection.Close();
}
return posts;
}
public static List<Tuple<string, long, long>> GetRepliesWithFilledText(string DBPath = @"TL.db", int limit = 1)
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
List<Tuple<string, long, long>> posts = new List<Tuple<string, long, long>>();
try
{
connection.Open();
string sql = @"SELECT DISTINCT Notes.RootBlogName as blogName, Notes.PostID,
MAX(Notes.timestamp) as LatestTimestamp
FROM Notes
WHERE Notes.type = 'reply'
AND (Notes.replyText IS NULL OR Notes.replyText = '' OR Notes.replyText = '.')
GROUP BY Notes.RootBlogName, Notes.PostID
ORDER BY LatestTimestamp ASC
LIMIT @limit";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@limit", limit);
using (SQLiteDataReader reader = command.ExecuteReader())
{
while (reader.Read())
{
Tuple<string, long, long> post = default;
string blog = null;
long id = 0;
long timestamp = 0;
blog = reader.GetString(reader.GetOrdinal("blogName"));
id = reader.GetInt64(reader.GetOrdinal("PostID"));
timestamp = reader.GetInt64(reader.GetOrdinal("LatestTimestamp"));
timestamp++;
post = new Tuple<string, long, long>(blog, id, timestamp);
posts.Add(post);
}
}
}
}
catch (Exception ex)
{
Console.WriteLine($"Error getting replies with filled text: {ex.Message}");
}
finally
{
connection.Close();
}
return posts;
}
public static int GetAPICount(string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
@@ -395,7 +559,7 @@ namespace URLNotesGrabberCORE
{
while (reader.Read())
{
count = reader.GetInt32(0); // Assuming Id is the first column
count = reader.GetInt32(0); // Assuming Id is the first column
}
}
}
@@ -510,7 +674,8 @@ namespace URLNotesGrabberCORE
{
connection.Open();
string sql = "UPDATE Posts SET HasNotesGathered = 1, NotesGatheredDateTime = @notesGathered WHERE BlogName = @BlogName AND PostID = @PostID";
//string sql = "UPDATE Posts SET HasNotesGathered = 1, NotesGatheredDateTime = @notesGathered WHERE BlogName = @BlogName AND PostID = @PostID";
string sql = "UPDATE Posts SET HasNotesGathered = 1, NotesGatheredDateTime = @notesGathered WHERE PostID = @PostID";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@notesGathered", DateTimeOffset.UtcNow.ToUnixTimeSeconds());
@@ -635,10 +800,10 @@ namespace URLNotesGrabberCORE
{
connection.Open();
string sql = "UPDATE Posts SET ";
string sql = "UPDATE Posts SET ";
sql += "postDate = @postDate, ";
sql += "reblogURL = @reblogURL, ";
sql += "postURL = @postURL, ";
sql += "postURL = @postURL, ";
sql += "slug = @slug, ";
sql += "reblogKey = @reblogKey, ";
sql += "reblogName = @reblogName, ";
@@ -752,8 +917,89 @@ namespace URLNotesGrabberCORE
}
return APICount;
}
public static void UpdateNoteReplyText(string rootBlogName, long postID, string noteBlogName, long timestamp, string replyText, string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
try
{
connection.Open();
//string sql = "UPDATE Notes SET replyText = @replyText WHERE rootBlogName = @rootBlogName AND PostID = @PostID AND noteBlogName = @noteBlogName AND TimeStamp = @TimeStamp AND Type = 'reply'";
string sql = "UPDATE Notes SET replyText = @replyText WHERE PostID = @PostID AND noteBlogName = @noteBlogName AND TimeStamp = @TimeStamp AND Type = 'reply'";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@replyText", replyText ?? ".");
command.Parameters.AddWithValue("@rootBlogName", rootBlogName);
command.Parameters.AddWithValue("@PostID", postID);
command.Parameters.AddWithValue("@noteBlogName", noteBlogName);
command.Parameters.AddWithValue("@TimeStamp", timestamp);
int rowsAffected = command.ExecuteNonQuery();
if (rowsAffected == 0)
{
Console.WriteLine($"[UpdateNoteReplyText] WARNING: No rows updated for {rootBlogName}/{postID} from {noteBlogName} at {UnixTimeStampToDateTime(timestamp)}");
Console.WriteLine($"[UpdateNoteReplyText] Query: {sql}");
Console.WriteLine($"[UpdateNoteReplyText] Params: rootBlogName={rootBlogName}, PostID={postID}, noteBlogName={noteBlogName}, TimeStamp={timestamp}");
}
else
{
Console.WriteLine($"[UpdateNoteReplyText] Successfully updated {rowsAffected} row(s) for {rootBlogName}/{postID} from {noteBlogName}");
}
}
}
#endregion Updates
catch (Exception ex)
{
Console.WriteLine($"[UpdateNoteReplyText] Error updating reply text: {ex.Message}");
Console.WriteLine($"[UpdateNoteReplyText] StackTrace: {ex.StackTrace}");
}
finally
{
connection.Close();
}
}
public static void UpdateAllNoteReplyTextForPost(string rootBlogName, long postID, string replyText, string DBPath = @"TL.db")
{
SQLiteConnection connection = new SQLiteConnection("Data Source=" + DBPath);
try
{
connection.Open();
string sql = "UPDATE Notes SET replyText = @replyText WHERE rootBlogName = @rootBlogName AND PostID = @PostID AND Type = 'reply'";
using (SQLiteCommand command = new SQLiteCommand(sql, connection))
{
command.Parameters.AddWithValue("@replyText", replyText ?? ".");
command.Parameters.AddWithValue("@rootBlogName", rootBlogName);
command.Parameters.AddWithValue("@PostID", postID);
int rowsAffected = command.ExecuteNonQuery();
if (rowsAffected == 0)
{
Console.WriteLine($"[UpdateAllNoteReplyTextForPost] WARNING: No rows updated for {rootBlogName}/{postID}");
Console.WriteLine($"[UpdateAllNoteReplyTextForPost] Query: {sql}");
Console.WriteLine($"[UpdateAllNoteReplyTextForPost] Params: rootBlogName={rootBlogName}, PostID={postID}, replyText={replyText}");
}
else
{
Console.WriteLine($"[UpdateAllNoteReplyTextForPost] Successfully updated {rowsAffected} row(s) for {rootBlogName}/{postID} with '{replyText}'");
}
}
}
catch (Exception ex)
{
Console.WriteLine($"[UpdateAllNoteReplyTextForPost] Error updating reply text: {ex.Message}");
Console.WriteLine($"[UpdateAllNoteReplyTextForPost] StackTrace: {ex.StackTrace}");
}
finally
{
connection.Close();
}
}
#endregion Updates
}
internal class APIAccess
@@ -772,35 +1018,38 @@ namespace URLNotesGrabberCORE
throw new InvalidOperationException("TumblrApi configuration is missing in appsettings.json");
}
private static string ConsumerKey => Configuration["TumblrApi:ConsumerKey"] ??
private static string ConsumerKey => Configuration["TumblrApi:ConsumerKey"] ??
throw new InvalidOperationException("ConsumerKey is not configured");
private static string ConsumerSecret => Configuration["TumblrApi:ConsumerSecret"] ??
private static string ConsumerSecret => Configuration["TumblrApi:ConsumerSecret"] ??
throw new InvalidOperationException("ConsumerSecret is not configured");
private static string OAuthToken => Configuration["TumblrApi:OAuthToken"] ??
throw new InvalidOperationException("OAuthToken is not configured");
private static string OAuthTokenSecret => Configuration["TumblrApi:OAuthTokenSecret"] ??
private static string OAuthToken => Configuration["TumblrApi:OAuthToken"] ??
throw new InvalidOperationException("OAuthToken is not configured");
private static string OAuthTokenSecret => Configuration["TumblrApi:OAuthTokenSecret"] ??
throw new InvalidOperationException("OAuthTokenSecret is not configured");
public static async Task<Root> GrabNotes(string blog, long ID, string? timestamp = null)
{
var URL = "https://api.tumblr.com/v2/blog/[0].tumblr.com/notes?id=[1]";
var URL = "https://api.tumblr.com/v2/blog/[0].tumblr.com/notes?id=[1]&mode=all";
URL = URL.Replace("[0]", blog).Replace("[1]", ID.ToString());
if (!string.IsNullOrEmpty(timestamp))
{
URL += "&before_timestamp=" + timestamp;
await Task.Delay(100);
}
var client = new RestClient(URL);
var oAuth1 = OAuth1Authenticator.ForAccessToken(consumerKey: ConsumerKey,
consumerSecret: ConsumerSecret,
token: OAuthToken,
tokenSecret: OAuthTokenSecret,
OAuthSignatureMethod.HmacSha1
);
// Create a new RestClient for each request to ensure fresh OAuth signatures
using (var client = new RestClient(URL))
{
var oAuth1 = OAuth1Authenticator.ForAccessToken(consumerKey: ConsumerKey,
consumerSecret: ConsumerSecret,
token: OAuthToken,
tokenSecret: OAuthTokenSecret,
OAuthSignatureMethod.HmacSha1
);
client.Authenticator = oAuth1;
var request = new RestRequest(URL, Method.Get);
var response = await client.ExecuteAsync(request);
client.Authenticator = oAuth1;
var request = new RestRequest(URL, Method.Get);
var response = await client.ExecuteAsync(request);
var myJsonResponse = response.Content ?? string.Empty;
Console.WriteLine($"{timestamp}\t{DateTime.Now}\t{DataAccess.UpdateAPICount()}");
@@ -864,8 +1113,8 @@ namespace URLNotesGrabberCORE
}
}
}
catch (Exception ex)
{
catch (Exception ex)
{
Console.WriteLine($"Failed JSON: {myJsonResponse}");
Console.WriteLine(ex.ToString());
@@ -939,7 +1188,7 @@ namespace URLNotesGrabberCORE
if (myDeserializedClass.retryInSeconds < secs)
myDeserializedClass.retryInSeconds = secs;
}
foundRateLimitHeader = true;
foundRateLimitHeader = true;
}
}
if (header.Name.Contains("Remaining", StringComparison.OrdinalIgnoreCase) && header.Value.ToString() == "0")
@@ -955,11 +1204,75 @@ namespace URLNotesGrabberCORE
myDeserializedClass.statusCode = "TooManyRequests";
}
}
}
}
}
}
return myDeserializedClass;
}
}
public static async Task<PostsRoot> GrabPostWithReplies(string blog, long postID, long timestamp)
{
var URL = $"https://api.tumblr.com/v2/blog/{Uri.EscapeDataString(blog)}.tumblr.com/posts?id={postID}&notes_info=true&before_timestamp={timestamp}";
// Create a new RestClient for each request to ensure fresh OAuth signatures
using (var client = new RestClient(URL))
{
var oAuth1 = OAuth1Authenticator.ForAccessToken(consumerKey: ConsumerKey,
consumerSecret: ConsumerSecret,
token: OAuthToken,
tokenSecret: OAuthTokenSecret,
OAuthSignatureMethod.HmacSha1
);
client.Authenticator = oAuth1;
var request = new RestRequest(URL, Method.Get);
var response = await client.ExecuteAsync(request);
var myJsonResponse = response.Content ?? string.Empty;
Console.WriteLine($"[Reply API] {DateTime.Now}\t{DataAccess.UpdateAPICount()}");
var myDeserializedClass = new PostsRoot();
// Check if response is successful and contains JSON
if (!response.IsSuccessful || string.IsNullOrEmpty(myJsonResponse))
{
string? statusStr = null;
try { statusStr = response != null ? response.StatusCode.ToString() : null; } catch { statusStr = null; }
Console.WriteLine($"[Reply API] {statusStr}\t{response?.StatusDescription}");
if (!string.IsNullOrEmpty(statusStr))
myDeserializedClass.statusCode = statusStr;
return myDeserializedClass;
}
// Check if response is HTML (error page) instead of JSON
if (myJsonResponse.TrimStart().StartsWith("<"))
{
Console.WriteLine($"[Reply API] Received HTML response (likely error page): {response?.StatusCode}");
string? statusStr = null;
try { statusStr = response != null ? response.StatusCode.ToString() : null; } catch { statusStr = null; }
if (!string.IsNullOrEmpty(statusStr))
myDeserializedClass.statusCode = statusStr;
return myDeserializedClass;
}
try
{
var deserializedResult = JsonConvert.DeserializeObject<PostsRoot>(myJsonResponse);
if (deserializedResult != null)
{
myDeserializedClass = deserializedResult;
myDeserializedClass.rawJson = myJsonResponse;
}
}
catch (Exception ex)
{
Console.WriteLine($"[Reply API] Failed to parse JSON response: {ex.Message}");
Console.WriteLine($"[Reply API] Response content: {myJsonResponse.Substring(0, Math.Min(200, myJsonResponse.Length))}");
}
return myDeserializedClass;
}
}
}
}
+334 -219
View File
@@ -26,9 +26,18 @@ namespace URLNotesGrabberCORE
if (File.Exists(logPath))
{
string timestamp = DateTime.Now.ToString("yyyyMMdd_HHmmss");
string newPath = $"console_output_{timestamp}.log";
string archiveDirectory = "logs";
// Ensure the archive directory exists
if (!Directory.Exists(archiveDirectory))
{
Directory.CreateDirectory(archiveDirectory);
}
string newPath = Path.Combine(archiveDirectory, $"console_output_{timestamp}.log");
File.Move(logPath, newPath);
}
StreamWriter fileWriter = new StreamWriter(logPath, append: false) { AutoFlush = true };
DualLogger dualLogger = new DualLogger(Console.Out, fileWriter);
Console.SetOut(dualLogger);
@@ -37,7 +46,9 @@ namespace URLNotesGrabberCORE
if (args.Length == 0) //Traverse folder structure to add posts and thus blogs to DB
{
TraverseDirectory(settings.GetValue<string>("PathInput"), settings.GetValue<string>("PathOutputBlogs"), contains);
int postsAdded = 0;
TraverseDirectory(settings.GetValue<string>("PathInput"), settings.GetValue<string>("PathOutputBlogs"), contains, ref postsAdded);
Console.WriteLine($"Total posts added: {postsAdded}");
}
else
{
@@ -56,102 +67,25 @@ namespace URLNotesGrabberCORE
Console.WriteLine("-blogs\t For each Blog in DB, write blogname to file");
Console.WriteLine("-collect\t For each Post in DB, hit API to collect Notes");
Console.WriteLine("-collect\t For each Post in DB, hit API to collect Notes. Optional datetime parameter to filter by NotesGatheredDateTime");
Console.WriteLine("-blogsR\t For each Note that is a REPLY, write blogname to file ");
Console.WriteLine("-blogsO\t For each Blog in DB, write blogname to file, but limit via a passed start and stop range ");
Console.WriteLine("-replies\t For each Note that is a REPLY, write blogname to file ");
break;
case "-parse":
string blogNameToParse = args[1];
TraverseDirectory(settings.GetValue<string>("PathInput"), settings.GetValue<string>("PathOutputBlogs"), contains, blogNameToParse);
Console.WriteLine("-replies\t Fetch and update missing reply text for all replies in database");
break;
case "-parse":
string blogNameToParse = args[1];
int postsAdded = 0;
TraverseDirectory(settings.GetValue<string>("PathInput"), settings.GetValue<string>("PathOutputBlogs"), contains, ref postsAdded, blogNameToParse);
Console.WriteLine($"Total posts added: {postsAdded}");
break;
case "-test":
#region Manual test
string blogName = args[1];
long postID = long.Parse(args[2]);
var response = APIAccess.GrabNotes(blogName, postID).GetAwaiter().GetResult();
List<Tuple<string, string>> notes = new List<Tuple<string, string>>();
// If the API returned a 404 inside the JSON `meta` block, mark the post NotFound
if (response?.meta != null && response.meta.status == 404)
{
Console.WriteLine($"ERROR: Post not found - {blogName}/{postID} (meta.status=404)");
DataAccess.UpdatePostMarkNotFound(blogName, postID);
break;
}
// Check for API errors
if (response.statusCode == "NotFound")
{
Console.WriteLine($"ERROR: Post not found - {blogName}/{postID}");
break;
}
if (response.statusCode == "TooManyRequests")
{
Console.WriteLine($"ERROR: Rate limited - retry in {response.retryInSeconds} seconds");
break;
}
if (!string.IsNullOrEmpty(response.statusCode))
{
Console.WriteLine($"ERROR: API returned status code: {response.statusCode}");
break;
}
// Check for null response
if (response.response == null)
{
Console.WriteLine("ERROR: API response is null");
break;
}
// Check for null notes
if (response.response.notes == null)
{
Console.WriteLine("ERROR: Notes collection is null (post may have 0 notes)");
break;
}
Console.WriteLine($"Processing {response.response.notes.Count} notes...");
foreach (var note in response.response.notes)
{
note.reblog_parent_blog_name = blogName; note.post_id = postID.ToString();
//notes.Add(new Tuple<string, string>(note.blog_url, note.type));
if (DataAccess.AddNote(note.reblog_parent_blog_name, note.blog_name, long.Parse(note.post_id), note.timestamp, note.type))
break;
}
while (response.response._links != null)
{
response = APIAccess.GrabNotes(blogName, postID, response.response._links.next.query_params.before_timestamp).GetAwaiter().GetResult();
if (response.response?.notes == null)
{
Console.WriteLine("ERROR: Notes collection became null during pagination");
break;
}
Console.WriteLine($"Processing {response.response.notes.Count} more notes...");
foreach (var note in response.response.notes)
{
note.reblog_parent_blog_name = blogName; note.post_id = postID.ToString(); ;
//notes.Add(new Tuple<string, string>(note.blog_url, note.type));
if (DataAccess.AddNote(note.reblog_parent_blog_name, note.blog_name, long.Parse(note.post_id), note.timestamp, note.type))
break;
}
}
Console.WriteLine("Test completed successfully");
#endregion
Console.WriteLine("Test command not implemented");
break;
case "-post":
@@ -168,13 +102,15 @@ namespace URLNotesGrabberCORE
case "-collect": //collect notes from all posts
bool withoutNotesOnly = true;
DateTime? beforeDate = DateTime.Now;
if(args.Length != 2)
if (args.Length < 2)
{
Console.WriteLine("--Expected WITHOUTNOTESONLY (0, 1)--");
Console.WriteLine("--Expected WITHOUTNOTESONLY (0, 1) [OPTIONAL: BEFOREDATE]--");
break;
}
// Parse withoutNotesOnly flag
if (args.Length > 1 && args[1] is not null)
{
if (args[1] == "1")
@@ -190,7 +126,23 @@ namespace URLNotesGrabberCORE
Console.WriteLine("Without Notes Only: {0}\t{1}", withoutNotesOnly, args[1]);
}
CollectNotes(settings.GetValue<string>("PathOutput"), withoutNotesOnly);
// Parse optional beforeDate parameter
if (args.Length >= 3 && !string.IsNullOrEmpty(args[2]))
{
if (DateTime.TryParse(args[2], out DateTime parsedDate))
{
beforeDate = parsedDate;
Console.WriteLine($"Filter: Collecting notes for posts with NotesGatheredDateTime < {beforeDate}");
}
else
{
Console.WriteLine($"ERROR: Invalid date format '{args[2]}'");
break;
}
}
CollectNotes(settings.GetValue<string>("PathOutput"), withoutNotesOnly, beforeDate);
break;
case "-blogsR": //collect notes from all posts
@@ -229,10 +181,8 @@ namespace URLNotesGrabberCORE
WriteBlogsToFileAll(settings.GetValue<string>("PathOutputBlogs"), false, from, to, top);
break;
case "-replies": //colection posts with replies
try { System.IO.File.Delete(settings.GetValue<string>("PathOutputReplies")); } catch { }
WriteRepliesToFile(settings.GetValue<string>("PathOutputBlogs"), false);
case "-replies": //update reply text
CollectMissingReplyText().GetAwaiter().GetResult();
break;
default:
@@ -249,7 +199,7 @@ namespace URLNotesGrabberCORE
static void WritePostBlogsToFile(string outPath)
{
List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts();
List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts();
using (StreamWriter sw = new StreamWriter(outPath, true))
{
@@ -333,16 +283,181 @@ namespace URLNotesGrabberCORE
return false;
}
static async Task FetchAndStoreReplyText(string blogName, long postID, long timestamp)
{
try
{
Console.WriteLine($"[Reply Text] Fetching reply text for {blogName}/{postID}/{timestamp}");
// Add 2-second delay before API call to avoid server-side rate limiting
await Task.Delay(2000);
var postsResponse = await APIAccess.GrabPostWithReplies(blogName, postID, timestamp);
if (postsResponse?.response?.posts == null || postsResponse.response.posts.Count == 0)
{
Console.WriteLine($"[Reply Text] No posts found in response for {blogName}/{postID}");
Console.WriteLine($"[Reply Text] Response Status Code: {postsResponse?.statusCode ?? "N/A"}");
Console.WriteLine($"[Reply Text] Response.response is null: {postsResponse?.response == null}");
if (postsResponse?.response != null)
{
Console.WriteLine($"[Reply Text] Posts count: {postsResponse.response.posts?.Count ?? 0}");
}
if (!string.IsNullOrEmpty(postsResponse?.rawJson))
{
Console.WriteLine($"[Reply Text] Raw Response JSON: {postsResponse.rawJson}");
}
// Mark all replies for this post with '?' to indicate API returned no posts
Console.WriteLine($"[Reply Text] Marking all replies for {blogName}/{postID} with '?' due to no posts in response");
DataAccess.UpdateAllNoteReplyTextForPost(blogName, postID, "?");
return;
}
// Get the first (and should be only) post
var post = postsResponse.response.posts.FirstOrDefault();
if (post?.notes == null)
{
Console.WriteLine($"[Reply Text] No notes found in post {blogName}/{postID}");
return;
}
Console.WriteLine($"[Reply Text] Found {post.notes.Count} total notes for {blogName}/{postID}");
// Update each reply with its text
int replyCount = 0;
int skippedCount = 0;
foreach (var note in post.notes)
{
if (note.type == "reply")
{
if (!string.IsNullOrEmpty(note.reply_text))
{
DataAccess.UpdateNoteReplyText(blogName, postID, note.blog_name, note.timestamp, note.reply_text);
replyCount++;
// Output the reply text being stored
string displayText = note.reply_text.Length > 100
? note.reply_text.Substring(0, 100) + "..."
: note.reply_text;
Console.WriteLine($" [{note.blog_name}] {displayText}");
}
else
{
skippedCount++;
Console.WriteLine($"[Reply Text] Skipped reply from {note.blog_name} - empty reply_text");
}
}
}
if (replyCount > 0)
{
Console.WriteLine($"[Reply Text] Updated {replyCount} reply texts for {blogName}/{postID}");
}
else
{
Console.WriteLine($"[Reply Text] No reply text found for {blogName}/{postID} (skipped: {skippedCount})");
}
// Mark any remaining replies with '.' as '?' to indicate they were processed but had no text
Console.WriteLine($"[Reply Text] Marking any remaining replies with '.' as '?' for {blogName}/{postID}");
//int cleanupCount = DataAccess.UpdateRemainingDefaultReplyText(blogName, postID, ".", "?");
//if (cleanupCount > 0)
//{
// Console.WriteLine($"[Reply Text] Cleaned up {cleanupCount} remaining replies for {blogName}/{postID}");
//}
}
catch (Exception ex)
{
Console.WriteLine($"[Reply Text] Error fetching reply text for {blogName}/{postID}: {ex.Message}");
Console.WriteLine($"[Reply Text] StackTrace: {ex.StackTrace}");
}
}
static async Task CollectMissingReplyText()
{
try
{
// Ensure the replyText column exists
DataAccess.EnsureReplyTextColumnExists();
Console.WriteLine("Starting collection of missing reply text...");
Console.WriteLine("Processing 10 posts at a time.");
int batchSize = 1; // Process 10 posts per batch
int totalProcessedCount = 0;
RateLimiter limiter = new SlidingWindowRateLimiter(new SlidingWindowRateLimiterOptions
{
PermitLimit = 300,
QueueProcessingOrder = QueueProcessingOrder.OldestFirst,
QueueLimit = 1,
Window = TimeSpan.FromMinutes(1),
SegmentsPerWindow = 60,
AutoReplenishment = true
});
while (true && totalProcessedCount < batchSize)
{
var postsWithFilledReplies = DataAccess.GetRepliesWithFilledText(limit: batchSize);
if (postsWithFilledReplies.Count == 0)
{
Console.WriteLine("No more posts with filled reply text found. Collection complete.");
break;
}
Console.WriteLine($"Found {postsWithFilledReplies.Count} posts with filled reply text. Processing batch...");
int batchProcessedCount = 0;
foreach (var post in postsWithFilledReplies)
{
using RateLimitLease lease = limiter.AttemptAcquire(1);
if (lease.IsAcquired)
{
Console.WriteLine($"Processing {post.Item1}/{post.Item2}/{post.Item3}");
await FetchAndStoreReplyText(post.Item1, post.Item2, post.Item3);
batchProcessedCount++;
totalProcessedCount++;
// Add 1 second delay between attempts
await Task.Delay(1000);
}
else
{
Console.WriteLine("!@@@@@@@ - Rate Limited Exceeded: No Lease Available");
Console.WriteLine($"Stopped after processing {totalProcessedCount} posts total");
return;
}
}
Console.WriteLine($"Batch complete. Processed {batchProcessedCount} posts in this batch.");
}
Console.WriteLine($"Completed collection of missing reply text. Total processed: {totalProcessedCount} posts.");
}
catch (Exception ex)
{
Console.WriteLine($"Error collecting missing reply text: {ex.Message}");
Console.WriteLine(ex.ToString());
}
}
static async Task<string> GrabNotes(Tuple<string, long, long, long> post)
{
try
{
int APICount = DataAccess.GetAPICount();
Console.WriteLine($"{post.Item1}\t{post.Item2}\t{DateTime.Now}\t{APICount}");
Thread.Sleep(3000);
Console.WriteLine(post.Item1 + '\t' + post.Item2 + '\t' + DateTime.Now + "\t" + APICount);
var response = APIAccess.GrabNotes(post.Item1, post.Item2, post.Item3.ToString()).GetAwaiter().GetResult();
// If the API returned a 404 inside the JSON `meta` block, mark the post NotFound and return
var allNotes = new List<dynamic>();
int page = 1;
string beforeTimestamp = post.Item3.ToString();
bool hasReplies = false;
const int maxPages = 500;
var response = APIAccess.GrabNotes(post.Item1, post.Item2, beforeTimestamp).GetAwaiter().GetResult();
// Handle 404 and error codes
if (response?.meta != null && response.meta.status == 404)
{
Console.WriteLine($"API returned 404 Not Found for {post.Item1}/{post.Item2} (meta.status=404)");
@@ -350,8 +465,11 @@ namespace URLNotesGrabberCORE
Thread.Sleep(1000);
return "NotFound";
}
List<Tuple<string, string>> notes = new List<Tuple<string, string>>();
if (response == null)
{
Console.WriteLine("##### Response is null - API Failure? ###");
return "FAILURE";
}
if (response.statusCode == "NotFound")
{
Thread.Sleep(1000);
@@ -368,86 +486,94 @@ namespace URLNotesGrabberCORE
return response.statusCode;
}
if (response.response != null && response.response.notes != null)
// Pagination loop
while (true)
{
Console.WriteLine("Notes\t" + response.response.notes.Count);
foreach (var note in response.response.notes)
{
note.reblog_parent_blog_name = post.Item1; note.post_id = post.Item2.ToString();
//notes.Add(new Tuple<string, string>(note.blog_url, note.type));
if (DataAccess.AddNote(note.reblog_parent_blog_name, note.blog_name, long.Parse(note.post_id), note.timestamp, note.type))
break;
}
}
else if (response.response == null)
{
Console.WriteLine("##### Response Null - API Failure? ###");
Console.WriteLine($"Raw JSON: {response.rawJson}");
return "FAILURE";
}
else if (response.response.notes == null)
{
Console.WriteLine("##### Notes Null - WHY? ###");
return "FAILURE";
}
else
{
while (response.response != null
&& response.response._links != null
&& long.Parse(response.response._links.next.query_params.before_timestamp) >= post.Item3)
{
response = APIAccess.GrabNotes(post.Item1, post.Item2, response.response._links.next.query_params.before_timestamp).GetAwaiter().GetResult();
if (response.response.notes is null)
{
Console.WriteLine("response.response.notes == null");
return "NULL NOTES";
}
int noteCount = response?.response?.notes?.Count ?? 0;
Console.WriteLine($"[GrabNotes] Page {page} | before_timestamp={beforeTimestamp} | Notes={noteCount}");
Console.WriteLine("Notes\t" + response.response.notes.Count);
foreach (var note in response.response.notes)
{
note.reblog_parent_blog_name = post.Item1; note.post_id = post.Item2.ToString();
//notes.Add(new Tuple<string, string>(note.blog_url, note.type));
if (DataAccess.AddNote(note.reblog_parent_blog_name, note.blog_name, long.Parse(note.post_id), note.timestamp, note.type))
break;
}
if (response?.response == null)
{
Console.WriteLine($"##### Response Null - API Failure? ###\nRaw JSON: {response?.rawJson}");
return "FAILURE";
}
if (response.response.notes == null)
{
Console.WriteLine("##### Notes Null - WHY? ###");
return "FAILURE";
}
// Accumulate notes
allNotes.AddRange(response.response.notes);
// Pagination: check for next
var nextLink = response.response._links?.next;
if (nextLink == null || string.IsNullOrEmpty(nextLink.query_params?.before_timestamp))
{
Console.WriteLine($"[GrabNotes] No more pages. Pagination complete after {page} page(s).");
break;
}
beforeTimestamp = nextLink.query_params.before_timestamp;
page++;
if (page > maxPages)
{
Console.WriteLine($"[GrabNotes] ERROR: Max page limit ({maxPages}) reached for {post.Item1}/{post.Item2}. Aborting further pagination.");
break;
}
// Fetch next page
response = APIAccess.GrabNotes(post.Item1, post.Item2, beforeTimestamp).GetAwaiter().GetResult();
}
Console.WriteLine($"[GrabNotes] Total notes accumulated: {allNotes.Count}");
// Process all accumulated notes
foreach (var note in allNotes)
{
note.reblog_parent_blog_name = post.Item1;
note.post_id = post.Item2.ToString();
if (note.type == "reply")
hasReplies = true;
DataAccess.AddNote(note.reblog_parent_blog_name, note.blog_name, long.Parse(note.post_id), note.timestamp, note.type);
}
return "Success";
}
catch(Exception ex) {
Console.WriteLine(ex.ToString()); }
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
return "UNKNOWN";
}
static async void CollectNotes(string outPath, bool withoutNotesOnly = true)
static async void CollectNotes(string outPath, bool withoutNotesOnly = true, DateTime? beforeDate = null)
{
List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts(withoutNotesOnly);
List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts(withoutNotesOnly, beforeDate);
RateLimiter limiter = new SlidingWindowRateLimiter(new SlidingWindowRateLimiterOptions {
PermitLimit = 300,
QueueProcessingOrder = QueueProcessingOrder.OldestFirst,
QueueLimit = 1,
Window = TimeSpan.FromMinutes(1),
SegmentsPerWindow = 60,
AutoReplenishment = true} );
RateLimiter limiter = new SlidingWindowRateLimiter(new SlidingWindowRateLimiterOptions
{
PermitLimit = 300,
QueueProcessingOrder = QueueProcessingOrder.OldestFirst,
QueueLimit = 1,
Window = TimeSpan.FromMinutes(1),
SegmentsPerWindow = 60,
AutoReplenishment = true
});
try
{
using (StreamWriter sw = new StreamWriter(outPath, true))
{
foreach (var post in posts)
while (posts.Count > 0)
{
var post = posts[0]; // Process the first post in the list
string status;
using RateLimitLease lease = limiter.AttemptAcquire(1);
if (lease.IsAcquired)
{
Console.WriteLine("{0,32} - {1,15} - {2}", post.Item1, post.Item2, DateTimeOffset.FromUnixTimeSeconds(post.Item4).ToString());
// Thread.Sleep(1000);
status = await GrabNotes(post);
}
else
@@ -455,10 +581,18 @@ namespace URLNotesGrabberCORE
Console.WriteLine("!@@@@@@@ - Rate Limited Exceeded: No Lease Available");
return;
}
if(status == "Success")
if (status == "Success")
{
DataAccess.UpdatePostMarkNotesCollected(post.Item1, post.Item2);
}
else
{
Console.WriteLine("GrabNotes Result: " + status);
}
// Re-fetch the updated list after processing the current post
posts = DataAccess.GetPosts(withoutNotesOnly, beforeDate);
}
}
}
@@ -469,38 +603,26 @@ namespace URLNotesGrabberCORE
}
static void TraverseDirectory(string path, string outPath, List<string> contains, string blogName = "")
static void TraverseDirectory(string path, string outPath, List<string> contains, ref int postsAdded, string blogName = "")
{
// Get all directories in the current directory and sort them alphabetically
var directories = Directory.GetDirectories(path);
Array.Sort(directories, StringComparer.InvariantCulture);
//using (StreamWriter sw = new StreamWriter(outPath, true))
//{
//sw.WriteLine("=====" + path);
//}
foreach (var directory in directories)
{
Console.WriteLine("Directory: " + directory);
TraverseDirectory(directory, outPath, contains, blogName); // Recursively traverse subdirectories
TraverseDirectory(directory, outPath, contains, ref postsAdded, blogName); // Recursively traverse subdirectories
}
try
{
bool headerWasWritten = false;
// Process all files in the current directory
foreach (var file in Directory.GetFiles(path))
{
if (file.EndsWith(".txt") && (path.Contains(blogName) || blogName == ""))
if (file.EndsWith(".txt", StringComparison.OrdinalIgnoreCase) && (string.IsNullOrEmpty(blogName) || path.IndexOf(blogName, StringComparison.OrdinalIgnoreCase) >= 0))
{
//Console.WriteLine($"=====File: {file}");
//using (StreamWriter sw = new StreamWriter(outPath, true))
//{
//sw.WriteLine("---" + file);
//}
try
{
var urls = new List<string>();
@@ -508,12 +630,11 @@ namespace URLNotesGrabberCORE
foreach (string line in File.ReadLines(file))
{
//if (line.StartsWith(@"Reblog url: https://") && !line.Contains(@"zombaee") && !line.Contains(@"zomb-eh") && !line.Contains(@"deactivated"))
if (line.StartsWith(@"Post id:"))
{ // if there were no files, let's still collect post info
if (line.StartsWith("Post id:", StringComparison.OrdinalIgnoreCase))
{
if (reblog.reblogName != "." && reblog.postID != "." && reblog.date != "." && reblog.reblogURL != "." && reblog.downloadedFiles == ".")
{
if (!reblog.reblogURL.Contains(@"deactivated")
if (!reblog.reblogURL.Contains("deactivated")
&& reblog.reblogURL.Length != 0
&& ContainsAny(reblog.reblogURL, contains))
{
@@ -522,119 +643,109 @@ namespace URLNotesGrabberCORE
{
headerWasWritten = true;
}
//if (reblog.reblogURL.Contains("/blog/private")
// || reblog.body.Contains("/blog/private"))
//{
// Console.WriteLine(reblog.postID);
// Console.WriteLine(reblog.postURL);
// Console.WriteLine(reblog.date);
// Console.WriteLine(reblog.body);
// Console.WriteLine(reblog.reblogKey);
// Console.WriteLine(reblog.reblogURL);
// Console.WriteLine(reblog.reblogName);
// Console.WriteLine(reblog.downloadedFiles);
//}
string curDir = currentDir.Name.Replace("_1", "").Replace("_2", "").Replace("_3", "").Replace("_4", "").Replace("_5", "").Replace("_6", "").Replace("_7", "").Replace("_8", "").Replace("_9", "");
urls.Add(string.Format("{0}\t{1}", curDir, reblog.postID));
DataAccess.AddPost(curDir, long.Parse(reblog.postID), reblog.reblogURL, reblog.date, reblog.postURL, reblog.slug, reblog.reblogKey,
reblog.reblogName, reblog.summary, reblog.quote, reblog.body, reblog.tags, reblog.link, reblog.photoURL,
reblog.photoCaption, reblog.downloadedFiles, reblog.audioCaption, reblog.question, reblog.answer,
reblog.title, false);
postsAdded++;
// Output hyperlink and post date
Console.WriteLine($"https://{reblog.reblogName}.tumblr.com/post/{reblog.postID} - {reblog.date}");
}
}
reblog = new ReblogRecord();
reblog.postID = line.Substring(9).Trim();
}
if (line.StartsWith(@"Reblog url:"))
if (line.StartsWith(@"Reblog url:", StringComparison.OrdinalIgnoreCase))
{
//reblog = new ReblogRecord();
reblog.reblogURL = line.Substring(12).Trim();
}
if (line.StartsWith(@"Reblog name:"))
if (line.StartsWith(@"Reblog name:", StringComparison.OrdinalIgnoreCase))
{
reblog.reblogName = line.Substring(13).Trim();
}
if (line.StartsWith(@"Downloaded files:"))
if (line.StartsWith(@"Downloaded files:", StringComparison.OrdinalIgnoreCase))
{
reblog.downloadedFiles = line.Substring(17).Trim();
}
if (line.StartsWith(@"Reblog key:"))
if (line.StartsWith(@"Reblog key:", StringComparison.OrdinalIgnoreCase))
{
reblog.reblogKey = line.Substring(11).Trim();
}
if (line.StartsWith(@"Date:"))
if (line.StartsWith(@"Date:", StringComparison.OrdinalIgnoreCase))
{
reblog.date = line.Substring(6).Trim();
}
if (line.StartsWith(@"Body:"))
if (line.StartsWith(@"Body:", StringComparison.OrdinalIgnoreCase))
{
reblog.body = line.Substring(6).Trim();
}
if (line.StartsWith(@"Post url:"))
if (line.StartsWith(@"Post url:", StringComparison.OrdinalIgnoreCase))
{
reblog.postURL = line.Substring(10).Trim();
}
if (line.StartsWith(@"Answer:"))
if (line.StartsWith(@"Answer:", StringComparison.OrdinalIgnoreCase))
{
reblog.answer = line.Substring(8).Trim();
}
if (line.StartsWith(@"Audio Caption:"))
if (line.StartsWith(@"Audio Caption:", StringComparison.OrdinalIgnoreCase))
{
reblog.audioCaption = line.Substring(15).Trim();
}
if (line.StartsWith(@"Blog Name:"))
if (line.StartsWith(@"Blog Name:", StringComparison.OrdinalIgnoreCase))
{
reblog.blogName = line.Substring(11).Trim();
}
if (line.StartsWith(@"Link:"))
if (line.StartsWith(@"Link:", StringComparison.OrdinalIgnoreCase))
{
reblog.link = line.Substring(6).Trim();
}
if (line.StartsWith(@"Photo Caption:"))
if (line.StartsWith(@"Photo Caption:", StringComparison.OrdinalIgnoreCase))
{
reblog.photoCaption = line.Substring(15).Trim();
}
if (line.StartsWith(@"Photo url:"))
if (line.StartsWith(@"Photo url:", StringComparison.OrdinalIgnoreCase))
{
reblog.photoURL = line.Substring(11).Trim();
}
if (line.StartsWith(@"Question:"))
if (line.StartsWith(@"Question:", StringComparison.OrdinalIgnoreCase))
{
reblog.question = line.Substring(10).Trim();
}
if (line.StartsWith(@"Quote:"))
if (line.StartsWith(@"Quote:", StringComparison.OrdinalIgnoreCase))
{
reblog.quote = line.Substring(7).Trim();
}
if (line.StartsWith(@"Slug:"))
if (line.StartsWith(@"Slug:", StringComparison.OrdinalIgnoreCase))
{
reblog.slug = line.Substring(6).Trim();
}
if (line.StartsWith(@"Summary:"))
if (line.StartsWith(@"Summary:", StringComparison.OrdinalIgnoreCase))
{
reblog.summary = line.Substring(9).Trim();
}
if (line.StartsWith(@"Tags:"))
if (line.StartsWith(@"Tags:", StringComparison.OrdinalIgnoreCase))
{
reblog.tags = line.Substring(6).Trim();
}
if (line.StartsWith(@"Title:"))
if (line.StartsWith(@"Title:", StringComparison.OrdinalIgnoreCase))
{
reblog.title = line.Substring(7).Trim();
}
if ((reblog.downloadedFiles != "."
|| reblog.reblogURL.Contains("/blog/private")
|| reblog.body.Contains("/blog/private")) && reblog.reblogName != "." && reblog.postID != "." && reblog.date != "." && reblog.reblogURL != ".")
|| (reblog.reblogURL?.IndexOf("/blog/private", StringComparison.OrdinalIgnoreCase) >= 0)
|| (reblog.body?.IndexOf("/blog/private", StringComparison.OrdinalIgnoreCase) >= 0)) && reblog.reblogName != "." && reblog.postID != "." && reblog.date != "." && reblog.reblogURL != ".")
{
if ((ContainsAny(reblog.downloadedFiles, contains)
|| reblog.reblogURL.Contains("/blog/private")
|| reblog.body.Contains("/blog/private"))
// && !ContainsAny(reblog.reblogURL, contains)
&& !reblog.reblogURL.Contains(@"deactivated"))
|| (reblog.reblogURL?.IndexOf("/blog/private", StringComparison.OrdinalIgnoreCase) >= 0)
|| (reblog.body?.IndexOf("/blog/private", StringComparison.OrdinalIgnoreCase) >= 0))
//&& !reblog.reblogURL.Contains("deactivated")
|| path.Contains("zomb-eh", StringComparison.InvariantCultureIgnoreCase))
{
DirectoryInfo currentDir = new DirectoryInfo(path);
if (!headerWasWritten)
@@ -659,6 +770,10 @@ namespace URLNotesGrabberCORE
reblog.reblogName, reblog.summary, reblog.quote, reblog.body, reblog.tags, reblog.link, reblog.photoURL,
reblog.photoCaption, reblog.downloadedFiles, reblog.audioCaption, reblog.question, reblog.answer,
reblog.title, true);
postsAdded++;
// Output hyperlink and post date
Console.WriteLine($"https://{reblog.reblogName}.tumblr.com/post/{reblog.postID} - {reblog.date}");
}
}
}
@@ -2,7 +2,7 @@
"profiles": {
"URLNotesGrabberCORE": {
"commandName": "Project",
"commandLineArgs": "-collect 0"
"commandLineArgs": "-collect 1"
}
}
}
+33
View File
@@ -83,4 +83,37 @@ namespace URLNotesGrabberCORE
public string rawJson { get; set; }
}
// Classes for Posts API endpoint (for reply_text)
public class PostsResponse
{
public List<Post> posts { get; set; }
}
public class Post
{
public long id { get; set; }
public List<NoteDetail> notes { get; set; }
}
public class NoteDetail
{
public long timestamp { get; set; }
public string type { get; set; }
public string blog_name { get; set; }
public string reply_text { get; set; }
}
public class PostsRoot
{
public Meta meta { get; set; }
[JsonConverter(typeof(EmptyArrayOrObjectConverter<PostsResponse>))]
public PostsResponse response { get; set; }
public string statusCode { get; set; }
public int retryInSeconds { get; set; }
public string rawJson { get; set; }
}
}
Binary file not shown.