jim
bc9985a6f0
- 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
852 lines
40 KiB
C#
852 lines
40 KiB
C#
using System.Threading.RateLimiting;
|
|
using Microsoft.Extensions.Http.Resilience;
|
|
using Microsoft.Extensions;
|
|
using Microsoft.Extensions.Configuration;
|
|
using System.Configuration;
|
|
using System.Threading;
|
|
using Microsoft.Extensions.Diagnostics.Latency;
|
|
using static System.Runtime.InteropServices.JavaScript.JSType;
|
|
|
|
namespace URLNotesGrabberCORE
|
|
{
|
|
internal class Program
|
|
{
|
|
|
|
static void Main(string[] args)
|
|
{
|
|
IConfiguration config = new ConfigurationBuilder()
|
|
.SetBasePath(Directory.GetCurrentDirectory())
|
|
.AddJsonFile("appsettings.json", optional: true, reloadOnChange: false)
|
|
.AddCommandLine(args)
|
|
.Build();
|
|
var settings = config.GetSection("appSettings");
|
|
|
|
// Setup Dual Logging
|
|
string logPath = "console_output.log";
|
|
if (File.Exists(logPath))
|
|
{
|
|
string timestamp = DateTime.Now.ToString("yyyyMMdd_HHmmss");
|
|
string archiveDirectory = "logs";
|
|
|
|
// Ensure the archive directory exists
|
|
if (!Directory.Exists(archiveDirectory))
|
|
{
|
|
Directory.CreateDirectory(archiveDirectory);
|
|
}
|
|
|
|
string newPath = Path.Combine(archiveDirectory, $"console_output_{timestamp}.log");
|
|
File.Move(logPath, newPath);
|
|
}
|
|
|
|
StreamWriter fileWriter = new StreamWriter(logPath, append: false) { AutoFlush = true };
|
|
DualLogger dualLogger = new DualLogger(Console.Out, fileWriter);
|
|
Console.SetOut(dualLogger);
|
|
|
|
List<string> contains = settings.GetValue<string>("ContainsList").Split(',').ToList();
|
|
|
|
if (args.Length == 0) //Traverse folder structure to add posts and thus blogs to DB
|
|
{
|
|
int postsAdded = 0;
|
|
TraverseDirectory(settings.GetValue<string>("PathInput"), settings.GetValue<string>("PathOutputBlogs"), contains, ref postsAdded);
|
|
Console.WriteLine($"Total posts added: {postsAdded}");
|
|
}
|
|
else
|
|
{
|
|
switch (args[0])
|
|
{
|
|
case "-?":
|
|
Console.WriteLine("\t Parse .txt files to find blogs");
|
|
|
|
Console.WriteLine("-?\t Usage help");
|
|
|
|
Console.WriteLine("-parse\t Parse .txt files with specified blogname");
|
|
|
|
Console.WriteLine("-test\t Calls API for given blogname and postID");
|
|
|
|
Console.WriteLine("-posts\t For each Post in DB, write blogname to file");
|
|
|
|
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. 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 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($"Total posts added: {postsAdded}");
|
|
break;
|
|
|
|
case "-test":
|
|
Console.WriteLine("Test command not implemented");
|
|
break;
|
|
|
|
case "-post":
|
|
TraverseDirectoryForCorruption(settings.GetValue<string>("PathInput"), settings.GetValue<string>("PathOutputBlogs"), contains);
|
|
break;
|
|
|
|
case "-posts": //write post's blogs to file
|
|
WritePostBlogsToFile(settings.GetValue<string>("PathOutputPosts"));
|
|
break;
|
|
|
|
case "-blogs": //write blogs to file
|
|
WriteBlogsToFile(settings.GetValue<string>("PathOutputBlogs"));
|
|
break;
|
|
|
|
case "-collect": //collect notes from all posts
|
|
bool withoutNotesOnly = true;
|
|
DateTime? beforeDate = DateTime.Now;
|
|
|
|
if (args.Length < 2)
|
|
{
|
|
Console.WriteLine("--Expected WITHOUTNOTESONLY (0, 1) [OPTIONAL: BEFOREDATE]--");
|
|
break;
|
|
}
|
|
|
|
// Parse withoutNotesOnly flag
|
|
if (args.Length > 1 && args[1] is not null)
|
|
{
|
|
if (args[1] == "1")
|
|
{
|
|
withoutNotesOnly = true;
|
|
Console.WriteLine("Parsed");
|
|
}
|
|
else
|
|
{
|
|
withoutNotesOnly = false;
|
|
Console.WriteLine("--NOT Parsed");
|
|
}
|
|
|
|
Console.WriteLine("Without Notes Only: {0}\t{1}", withoutNotesOnly, args[1]);
|
|
}
|
|
|
|
// Parse optional beforeDate parameter
|
|
if (args.Length >= 3 && !string.IsNullOrEmpty(args[2]))
|
|
{
|
|
if (DateTime.TryParse(args[2], out DateTime parsedDate))
|
|
{
|
|
beforeDate = parsedDate;
|
|
Console.WriteLine($"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
|
|
WriteBlogsToFile(settings.GetValue<string>("PathOutputBlogs"), true);
|
|
break;
|
|
|
|
case "-blogsO": //collect notes from all posts
|
|
int from = 1, to = 999999, top = 100;
|
|
|
|
if (args[1] is not null && args[2] is not null && args[3] is not null)
|
|
{
|
|
from = int.Parse(args[1]);
|
|
to = int.Parse(args[2]);
|
|
top = int.Parse(args[3]);
|
|
}
|
|
else
|
|
{
|
|
Console.WriteLine("--Expected FROM TO--");
|
|
}
|
|
WriteBlogsToFile(settings.GetValue<string>("PathOutputBlogs"), false, from, to, top);
|
|
break;
|
|
|
|
case "-bop": //collect notes from all posts
|
|
from = 1; to = 999999; top = 100;
|
|
|
|
if (args[1] is not null && args[2] is not null && args[3] is not null)
|
|
{
|
|
from = int.Parse(args[1]);
|
|
to = int.Parse(args[2]);
|
|
top = int.Parse(args[3]);
|
|
}
|
|
else
|
|
{
|
|
Console.WriteLine("--Expected FROM TO--");
|
|
}
|
|
WriteBlogsToFileAll(settings.GetValue<string>("PathOutputBlogs"), false, from, to, top);
|
|
break;
|
|
|
|
case "-replies": //update reply text
|
|
CollectMissingReplyText().GetAwaiter().GetResult();
|
|
break;
|
|
|
|
default:
|
|
Console.WriteLine("** Unknown Command ** " + args[0]);
|
|
break;
|
|
}
|
|
}
|
|
|
|
|
|
|
|
System.Console.WriteLine("<fin>:/");
|
|
//System.Console.ReadKey();
|
|
}
|
|
|
|
static void WritePostBlogsToFile(string outPath)
|
|
{
|
|
List<Tuple<string, long, long, long>> posts = DataAccess.GetPosts();
|
|
|
|
using (StreamWriter sw = new StreamWriter(outPath, true))
|
|
{
|
|
List<string> blogs = new List<string>();
|
|
foreach (var post in posts)
|
|
{
|
|
blogs.Add(post.Item1);
|
|
}
|
|
blogs = blogs.Distinct().ToList();
|
|
blogs.Sort();
|
|
blogs.Reverse();
|
|
|
|
foreach (var blog in blogs)
|
|
{
|
|
Console.WriteLine(blog);
|
|
sw.WriteLine(blog + ".tumblr.com");
|
|
}
|
|
}
|
|
}
|
|
|
|
static void WriteBlogsToFile(string outPath, bool reblogsOnly = false, int from = 0, int to = 999999, int top = 100)
|
|
{
|
|
List<string> blogs = DataAccess.GetBlogs(reblogsOnly, from, to, top);
|
|
blogs.Sort();
|
|
blogs.Reverse();
|
|
|
|
using (StreamWriter sw = new StreamWriter(outPath, true))
|
|
{
|
|
foreach (var blog in blogs)
|
|
{
|
|
Console.WriteLine(blog);
|
|
sw.WriteLine(blog + ".tumblr.com");
|
|
DataAccess.UpdateBlogOutput(blog);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void WriteBlogsToFileAll(string outPath, bool reblogsOnly = false, int from = 0, int to = 999999, int top = 100)
|
|
{
|
|
List<string> blogs = DataAccess.GetBlogsAll(reblogsOnly, from, to, top);
|
|
blogs.Sort();
|
|
blogs.Reverse();
|
|
|
|
using (StreamWriter sw = new StreamWriter(outPath, true))
|
|
{
|
|
foreach (var blog in blogs)
|
|
{
|
|
Console.WriteLine(blog);
|
|
sw.WriteLine(blog + ".tumblr.com");
|
|
DataAccess.UpdateBlogOutput(blog);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void WriteRepliesToFile(string outPath, bool reblogsOnly = false)
|
|
{
|
|
List<Tuple<string, long>> posts = DataAccess.GetReplies();
|
|
|
|
using (StreamWriter sw = new StreamWriter(outPath, true))
|
|
{
|
|
foreach (var post in posts)
|
|
{
|
|
Console.WriteLine(@"https://tumblr.com/{0}/{1}", post.Item1, post.Item2);
|
|
sw.WriteLine(@"https://tumblr.com/{0}/{1}", post.Item1, post.Item2);
|
|
}
|
|
}
|
|
}
|
|
|
|
protected static bool ContainsAny(string input, List<string> contains)
|
|
{
|
|
if (string.IsNullOrEmpty(input)) return false;
|
|
|
|
|
|
foreach (string item in contains)
|
|
{
|
|
if (input.IndexOf(item, StringComparison.OrdinalIgnoreCase) >= 0)
|
|
{
|
|
return true;
|
|
}
|
|
}
|
|
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($"{post.Item1}\t{post.Item2}\t{DateTime.Now}\t{APICount}");
|
|
Thread.Sleep(3000);
|
|
|
|
var allNotes = new List<dynamic>();
|
|
int page = 1;
|
|
string beforeTimestamp = post.Item3.ToString();
|
|
bool hasReplies = false;
|
|
const int maxPages = 500;
|
|
var response = APIAccess.GrabNotes(post.Item1, post.Item2, beforeTimestamp).GetAwaiter().GetResult();
|
|
|
|
// Handle 404 and error codes
|
|
if (response?.meta != null && response.meta.status == 404)
|
|
{
|
|
Console.WriteLine($"API returned 404 Not Found for {post.Item1}/{post.Item2} (meta.status=404)");
|
|
DataAccess.UpdatePostMarkNotFound(post.Item1, post.Item2);
|
|
Thread.Sleep(1000);
|
|
return "NotFound";
|
|
}
|
|
if (response == null)
|
|
{
|
|
Console.WriteLine("##### Response is null - API Failure? ###");
|
|
return "FAILURE";
|
|
}
|
|
if (response.statusCode == "NotFound")
|
|
{
|
|
Thread.Sleep(1000);
|
|
DataAccess.UpdatePostMarkNotFound(post.Item1, post.Item2);
|
|
return response.statusCode;
|
|
}
|
|
if (response.statusCode == "TooManyRequests")
|
|
{
|
|
for (int s = 0; s <= response.retryInSeconds; s += 15)
|
|
{
|
|
Console.WriteLine("Sleeping for {0} more seconds, until {1}", response.retryInSeconds - s, DateTime.Now.AddSeconds(response.retryInSeconds - s).ToShortTimeString());
|
|
Thread.Sleep(15000);
|
|
}
|
|
return response.statusCode;
|
|
}
|
|
|
|
// Pagination loop
|
|
while (true)
|
|
{
|
|
int noteCount = response?.response?.notes?.Count ?? 0;
|
|
Console.WriteLine($"[GrabNotes] Page {page} | before_timestamp={beforeTimestamp} | Notes={noteCount}");
|
|
|
|
if (response?.response == null)
|
|
{
|
|
Console.WriteLine($"##### 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());
|
|
}
|
|
return "UNKNOWN";
|
|
}
|
|
|
|
static async void CollectNotes(string outPath, bool withoutNotesOnly = true, DateTime? beforeDate = null)
|
|
{
|
|
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
|
|
});
|
|
|
|
try
|
|
{
|
|
using (StreamWriter sw = new StreamWriter(outPath, true))
|
|
{
|
|
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());
|
|
status = await GrabNotes(post);
|
|
}
|
|
else
|
|
{
|
|
Console.WriteLine("!@@@@@@@ - Rate Limited Exceeded: No Lease Available");
|
|
return;
|
|
}
|
|
|
|
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);
|
|
}
|
|
}
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
Console.WriteLine(ex.ToString());
|
|
}
|
|
}
|
|
|
|
|
|
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);
|
|
|
|
foreach (var directory in directories)
|
|
{
|
|
Console.WriteLine("Directory: " + directory);
|
|
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", StringComparison.OrdinalIgnoreCase) && (string.IsNullOrEmpty(blogName) || path.IndexOf(blogName, StringComparison.OrdinalIgnoreCase) >= 0))
|
|
{
|
|
try
|
|
{
|
|
var urls = new List<string>();
|
|
var reblog = new ReblogRecord();
|
|
|
|
foreach (string line in File.ReadLines(file))
|
|
{
|
|
if (line.StartsWith("Post id:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
if (reblog.reblogName != "." && reblog.postID != "." && reblog.date != "." && reblog.reblogURL != "." && reblog.downloadedFiles == ".")
|
|
{
|
|
if (!reblog.reblogURL.Contains("deactivated")
|
|
&& reblog.reblogURL.Length != 0
|
|
&& ContainsAny(reblog.reblogURL, contains))
|
|
{
|
|
DirectoryInfo currentDir = new DirectoryInfo(path);
|
|
if (!headerWasWritten)
|
|
{
|
|
headerWasWritten = true;
|
|
}
|
|
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:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
//reblog = new ReblogRecord();
|
|
|
|
reblog.reblogURL = line.Substring(12).Trim();
|
|
}
|
|
if (line.StartsWith(@"Reblog name:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.reblogName = line.Substring(13).Trim();
|
|
}
|
|
if (line.StartsWith(@"Downloaded files:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.downloadedFiles = line.Substring(17).Trim();
|
|
}
|
|
if (line.StartsWith(@"Reblog key:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.reblogKey = line.Substring(11).Trim();
|
|
}
|
|
if (line.StartsWith(@"Date:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.date = line.Substring(6).Trim();
|
|
}
|
|
if (line.StartsWith(@"Body:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.body = line.Substring(6).Trim();
|
|
}
|
|
if (line.StartsWith(@"Post url:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.postURL = line.Substring(10).Trim();
|
|
}
|
|
if (line.StartsWith(@"Answer:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.answer = line.Substring(8).Trim();
|
|
}
|
|
if (line.StartsWith(@"Audio Caption:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.audioCaption = line.Substring(15).Trim();
|
|
}
|
|
if (line.StartsWith(@"Blog Name:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.blogName = line.Substring(11).Trim();
|
|
}
|
|
if (line.StartsWith(@"Link:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.link = line.Substring(6).Trim();
|
|
}
|
|
if (line.StartsWith(@"Photo Caption:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.photoCaption = line.Substring(15).Trim();
|
|
}
|
|
if (line.StartsWith(@"Photo url:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.photoURL = line.Substring(11).Trim();
|
|
}
|
|
if (line.StartsWith(@"Question:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.question = line.Substring(10).Trim();
|
|
}
|
|
if (line.StartsWith(@"Quote:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.quote = line.Substring(7).Trim();
|
|
}
|
|
if (line.StartsWith(@"Slug:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.slug = line.Substring(6).Trim();
|
|
}
|
|
if (line.StartsWith(@"Summary:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.summary = line.Substring(9).Trim();
|
|
}
|
|
if (line.StartsWith(@"Tags:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.tags = line.Substring(6).Trim();
|
|
}
|
|
if (line.StartsWith(@"Title:", StringComparison.OrdinalIgnoreCase))
|
|
{
|
|
reblog.title = line.Substring(7).Trim();
|
|
}
|
|
|
|
if ((reblog.downloadedFiles != "."
|
|
|| (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?.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)
|
|
{
|
|
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, true);
|
|
postsAdded++;
|
|
|
|
// Output hyperlink and post date
|
|
Console.WriteLine($"https://{reblog.reblogName}.tumblr.com/post/{reblog.postID} - {reblog.date}");
|
|
}
|
|
}
|
|
}
|
|
urls.Sort();
|
|
|
|
|
|
//using (StreamWriter sw = new StreamWriter(outPath, true))
|
|
//{
|
|
// foreach (string line in urls.Distinct())
|
|
// {
|
|
// sw.WriteLine(line);
|
|
// }
|
|
//}
|
|
}
|
|
catch (Exception e)
|
|
{
|
|
Console.WriteLine("The file could not be read:");
|
|
Console.WriteLine(e.Message);
|
|
}
|
|
}
|
|
// Add your file processing logic here
|
|
}
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
Console.WriteLine($"An error occurred: {ex.Message}");
|
|
}
|
|
}
|
|
|
|
|
|
static void TraverseDirectoryForCorruption(string path, string outPath, List<string> contains, string blogName = "")
|
|
{
|
|
var directories = Directory.GetDirectories(path);
|
|
Array.Sort(directories, StringComparer.InvariantCulture);
|
|
|
|
foreach (var directory in directories)
|
|
{
|
|
//Console.WriteLine("Directory: " + directory);
|
|
TraverseDirectoryForCorruption(directory, outPath, contains, blogName); // Recursively traverse subdirectories
|
|
}
|
|
try
|
|
{
|
|
bool headerWasWritten = false;
|
|
foreach (var file in Directory.GetFiles(path))
|
|
{
|
|
if (file.EndsWith(".txt") && (path.Contains(blogName) || blogName == ""))
|
|
{
|
|
try
|
|
{
|
|
var urls = new List<string>();
|
|
var reblog = new ReblogRecord();
|
|
|
|
foreach (string line in File.ReadLines(file))
|
|
{
|
|
if (!line.StartsWith(@"Post id:") && line.Contains(@"id:"))
|
|
{
|
|
Console.WriteLine(file);
|
|
}
|
|
}
|
|
}
|
|
catch (Exception e)
|
|
{
|
|
Console.WriteLine("The file could not be read:");
|
|
Console.WriteLine(e.Message);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
Console.WriteLine($"An error occurred: {ex.Message}");
|
|
}
|
|
}
|
|
}
|
|
}
|