Fix #51: These last days the algorithm seems to not treat completely firstly the starting set of channels before treating discovered channels

I verified that this commit solves the issue by treating only `CHANNELS` tab of the channels in `channels.txt`.

main.cpp

@@ -60,7 +60,8 @@ string CHANNELS_DIRECTORY = "channels/",
        YOUTUBE_OPERATIONAL_API_INSTANCE_URL = "http://localhost/YouTube-operational-API", // Can be "https://yt.lemnoslife.com" for instance.
        CAPTIONS_DIRECTORY = "captions/",
        DEBUG_DIRECTORY = "debug/",
-       YOUTUBE_API_REQUESTS_DIRECTORY = "requests/";
+       YOUTUBE_API_REQUESTS_DIRECTORY = "requests/",
+       CURRENT_WORKING_DIRECTORY;
 bool USE_YT_LEMNOSLIFE_COM_NO_KEY_SERVICE = false;
 
 int main(int argc, char *argv[])
@@ -129,6 +130,13 @@ int main(int argc, char *argv[])
         }
     }
 
+    char cwd[PATH_MAX];
+    if (getcwd(cwd, sizeof(cwd)) != NULL) {
+        CURRENT_WORKING_DIRECTORY = string(cwd) + "/";
+    } else {
+        MAIN_EXIT_WITH_ERROR("`getcwd()` error");
+    }
+
     MAIN_PRINT(channelsToTreat.size() << " channel(s) to treat")
     MAIN_PRINT(channelsAlreadyTreated.size() << " channel(s) already treated")
 
@@ -194,13 +202,13 @@ void treatChannels(unsigned short threadId)
         // As I haven't found any well-known library that compress easily a directory, I have chosen to rely on `zip` cli.
         // We precise no `debug`ging, as otherwise the zipping operation doesn't work as expected.
         // As the zipping process isn't recursive, we can't just rely on `ls`, but we are obliged to use `find`.
-        exec(threadId, "cd " + channelToTreatDirectory + " && find | zip ../" + channelToTreat + ".zip -@", false);
+        exec(threadId, "cd " + channelToTreatDirectory + " && find | zip ../" + channelToTreat + ".zip -@");
 
         PRINT("Compression finished, started deleting initial directory...")
         deleteDirectory(channelToTreatDirectory);
         PRINT("Deleting directory finished.")
 
-        PRINT(channelsCountThreads[threadId] << " comments were found for this channel.")
+        PRINT(channelsCountThreads[threadId] << " channels were found for this channel.")
     }
 
     channelsAlreadyTreatedAndToTreatMutex.unlock();
@@ -577,7 +585,9 @@ void treatChannelOrVideo(unsigned short threadId, bool isChannel, string id, str
             json data = getJson(threadId, "playlistItems?part=snippet,contentDetails,status&playlistId=" + playlistToTreat + "&maxResults=50&pageToken=" + pageToken, true, channelToTreat, returnErrorIfPlaylistNotFound);
             if(data.contains("error"))
             {
-                EXIT_WITH_ERROR("Not listing captions on videos, as `playlistItems` hasn't found the `uploads` playlist!")
+                // `UCFoBM1VginhMH7lR56GtVbQ` doesn't have videos and is in this case for instance.
+                PRINT("Not listing captions on videos, as `playlistItems` hasn't found the `uploads` playlist!")
+                break;
             }
             json items = data["items"];
             for(const auto& item : items)
@@ -594,7 +604,7 @@ void treatChannelOrVideo(unsigned short threadId, bool isChannel, string id, str
                 // We are obliged to precise the video id after `--`, otherwise if the video id starts with `-` it's considered as an argument.
                 string cmdCommonPrefix = "yt-dlp --skip-download ",
                        cmdCommonPostfix = " -o '" + channelCaptionsToTreatDirectory + "_' -- " + videoId;
-                string cmd = cmdCommonPrefix + "--sub-lang all,-live_chat" + cmdCommonPostfix;
+                string cmd = cmdCommonPrefix + "--write-sub --sub-lang all,-live_chat" + cmdCommonPostfix;
                 exec(threadId, cmd);
 
                 // Secondly download the automatically generated captions.
@@ -621,7 +631,8 @@ void addChannelToTreat(unsigned short threadId, string channelId)
     channelsAlreadyTreatedAndToTreatMutex.lock();
     if(channelsAlreadyTreated.find(channelId) == channelsAlreadyTreated.end() && channelsToTreatRev.find(channelId) == channelsToTreatRev.end())
     {
-        unsigned int channelsToTreatIndex = channelsToTreat.end()->first + 1;
+        // It is unclear to me why `channelsToTreat.end()->first + 1` doesn't work here.
+        unsigned int channelsToTreatIndex = channelsToTreat.rbegin()->first + 1;
         channelsToTreat[channelsToTreatIndex] = channelId;
         channelsToTreatRev[channelId] = channelsToTreatIndex;
 
@@ -669,12 +680,14 @@ void exec(unsigned short threadId, string cmd, bool debug)
         toString << threadId;
         string initialCmd = cmd,
                threadIdStr = toString.str(),
-               debugCommonFilePath = DEBUG_DIRECTORY + threadIdStr,
+               debugCommonFilePath = CURRENT_WORKING_DIRECTORY + DEBUG_DIRECTORY + threadIdStr,
                debugOutFilePath = debugCommonFilePath + ".out",
                debugErrFilePath = debugCommonFilePath + ".err";
         cmd += " >> " + debugOutFilePath;
         cmd += " 2>> " + debugErrFilePath;
-        cmd += "; echo \"" + initialCmd + "\" | tee -a " + debugOutFilePath + " " + debugErrFilePath;
+
+        writeFile(threadId, debugOutFilePath, "a", initialCmd + "\n");
+        writeFile(threadId, debugErrFilePath, "a", initialCmd + "\n");
     }
     system(cmd.c_str());
 }

removeChannelsBeingTreated.py

@@ -14,7 +14,8 @@ with open('nohup.out') as f:
             #print(line)
             threadId = line.split(': ')[1]
             channelId = line.split(infix)[1].split(' (')[0]
-            threads[threadId] = channelId
+            if threadId.isdigit() and channelId.startswith('UC') and len(channelId) == 24:
+                threads[threadId] = channelId
     for threadId in threads:
         channelId = threads[threadId]
         print(threadId, channelId)