Benjamin_Loison/YouTube_captions_search_engine
Benjamin_Loison/YouTube_captions_search_engine
1
0
Fork 0
Code Issues 16 Pull Requests Packages Projects Releases 2 Wiki Activity

Fix #23: YouTube Data API v3 PlaylistItems: list endpoint returns playlistNotFound error for regular uploads ones

Browse Source
This commit is contained in:
Benjamin Loison 2023-01-08 16:31:57 +01:00
parent b3779fe49a
commit d6f6b26361
Signed by: Benjamin_Loison
SSH Key Fingerprint: SHA256:BtnEgYTlHdOg1u+RmYcDE0mnfz1rhv5dSbQ2gyxW8B8
1 changed files with 22 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
main.cpp
View File

@ -12,8 +12,10 @@ using namespace std;
using namespace chrono; using namespace chrono;
using json = nlohmann::json; using json = nlohmann::json;
enum getJsonBehavior { normal, retryOnCommentsDisabled, returnErrorIfPlaylistNotFound };
vector<string> getFileContent(string filePath); vector<string> getFileContent(string filePath);
json getJson(unsigned short threadId, string url, string directoryPath, bool retryOnCommentsDisabled = false); json getJson(unsigned short threadId, string url, string directoryPath, getJsonBehavior behavior = normal);
void createDirectory(string path), void createDirectory(string path),
print(ostringstream* toPrint), print(ostringstream* toPrint),
treatComment(unsigned short threadId, json comment, string channelId), treatComment(unsigned short threadId, json comment, string channelId),
@ -139,7 +141,7 @@ void treatChannelOrVideo(unsigned short threadId, bool isChannel, string id, str
ostringstream toString; ostringstream toString;
toString << "commentThreads?part=snippet,replies&" << (isChannel ? "allThreadsRelatedToChannelId" : "videoId") << "=" << id << "&maxResults=100&pageToken=" << pageToken; toString << "commentThreads?part=snippet,replies&" << (isChannel ? "allThreadsRelatedToChannelId" : "videoId") << "=" << id << "&maxResults=100&pageToken=" << pageToken;
string url = toString.str(); string url = toString.str();
json data = getJson(threadId, url, channelToTreat, pageToken != ""); json data = getJson(threadId, url, channelToTreat, pageToken == "" ? normal : retryOnCommentsDisabled);
bool doesRelyingOnCommentThreadsIsEnough = (!isChannel) || data["error"]["errors"][0]["reason"] != "commentsDisabled"; bool doesRelyingOnCommentThreadsIsEnough = (!isChannel) || data["error"]["errors"][0]["reason"] != "commentsDisabled";
if(doesRelyingOnCommentThreadsIsEnough) if(doesRelyingOnCommentThreadsIsEnough)
{ {
@ -199,15 +201,20 @@ void treatChannelOrVideo(unsigned short threadId, bool isChannel, string id, str
unsigned int videoCount = atoi(string(data["items"][0]["statistics"]["videoCount"]).c_str()); unsigned int videoCount = atoi(string(data["items"][0]["statistics"]["videoCount"]).c_str());
PRINT(threadId, "The channel has about " << videoCount << " videos.") PRINT(threadId, "The channel has about " << videoCount << " videos.")
// `UC-3A9g4U1PpLaeAuD4jSP_w` has a `videoCount` of 2, while its `uploads` playlist contains 3 videos. So we use a strict inequality here. // `UC-3A9g4U1PpLaeAuD4jSP_w` has a `videoCount` of 2, while its `uploads` playlist contains 3 videos. So we use a strict inequality here.
if(videoCount < 20000) if(0 < videoCount && videoCount < 20000)
{ {
string playlistToTreat = "UU" + channelToTreat.substr(2), string playlistToTreat = "UU" + channelToTreat.substr(2),
pageToken = ""; pageToken = "";
while(true) while(true)
{ {
// `snippet` and `status` are unneeded `part`s here but may be interesting later, as we log them. // `snippet` and `status` are unneeded `part`s here but may be interesting later, as we log them.
json data = getJson(threadId, "playlistItems?part=snippet,contentDetails,status&playlistId=" + playlistToTreat + "&maxResults=50&pageToken=" + pageToken, channelToTreat), json data = getJson(threadId, "playlistItems?part=snippet,contentDetails,status&playlistId=" + playlistToTreat + "&maxResults=50&pageToken=" + pageToken, channelToTreat, returnErrorIfPlaylistNotFound);
items = data["items"]; if(data.contains("error"))
{
PRINT(threadId, "Not listing comments on videos, as `playlistItems` hasn't found the `uploads` playlist!")
exit(1);
}
json items = data["items"];
for(const auto& item : items) for(const auto& item : items)
{ {
string videoId = item["contentDetails"]["videoId"]; string videoId = item["contentDetails"]["videoId"];
@ -226,7 +233,12 @@ void treatChannelOrVideo(unsigned short threadId, bool isChannel, string id, str
} }
break; break;
} }
else else if(videoCount == 0)
{
PRINT(threadId, "Skip listing comments on videos, as they shouldn't be any according to `channels?part=statistics`.")
break;
}
else //if(videoCount >= 20000)
{ {
PRINT(threadId, "The videos count of the channel exceeds the supported 20,000 limit!") PRINT(threadId, "The videos count of the channel exceeds the supported 20,000 limit!")
exit(1); exit(1);
@ -330,7 +342,7 @@ vector<string> getFileContent(string filePath)
return lines; return lines;
} }
json getJson(unsigned short threadId, string url, string directoryPath, bool retryOnCommentsDisabled) json getJson(unsigned short threadId, string url, string directoryPath, getJsonBehavior behavior)
{ {
#ifdef USE_YT_LEMNOSLIFE_COM_NO_KEY_SERVICE #ifdef USE_YT_LEMNOSLIFE_COM_NO_KEY_SERVICE
string finalUrl = "https://yt.lemnoslife.com/noKey/" + url; string finalUrl = "https://yt.lemnoslife.com/noKey/" + url;
@ -352,9 +364,10 @@ json getJson(unsigned short threadId, string url, string directoryPath, bool ret
if(data.contains("error")) if(data.contains("error"))
{ {
PRINT(threadId, "Found error in JSON at URL: " << finalUrl << " for content: " << content << " !") PRINT(threadId, "Found error in JSON at URL: " << finalUrl << " for content: " << content << " !")
if(data["error"]["errors"][0]["reason"] != "commentsDisabled" || retryOnCommentsDisabled) string reason = data["error"]["errors"][0]["reason"];
if(reason != "commentsDisabled" || behavior == retryOnCommentsDisabled)
{ {
return getJson(threadId, url, directoryPath); return reason == "playlistNotFound" && behavior == returnErrorIfPlaylistNotFound ? data : getJson(threadId, url, directoryPath);
} }
} }