From 902d2084f138fbdc40717dc9c85d47c8c5b9e6bf Mon Sep 17 00:00:00 2001
From: Benjamin Loison <benjamin.loison@orange.fr>
Date: Thu, 27 Apr 2023 00:01:58 +0200
Subject: [PATCH] Add `README.md` and `search_in_youtube_video_comments.py`

---
 README.md                           |  1 +
 search_in_youtube_video_comments.py | 51 +++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 README.md
 create mode 100644 search_in_youtube_video_comments.py

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..b297956
--- /dev/null
+++ b/README.md
@@ -0,0 +1 @@
+# Search in YouTube video comments
diff --git a/search_in_youtube_video_comments.py b/search_in_youtube_video_comments.py
new file mode 100644
index 0000000..fb8336b
--- /dev/null
+++ b/search_in_youtube_video_comments.py
@@ -0,0 +1,51 @@
+import requests, json, os, re
+
+def getContentFromURL(url):
+    #url = f'https://yt.lemnoslife.com/noKey/{url}'
+    url = f'https://www.googleapis.com/youtube/v3/{url}&key={API_KEY}'
+    #print(url)
+    content = requests.get(url).text
+    data = json.loads(content)
+    return data
+
+VIDEO_ID = '5PdEmeopJVQ'
+API_KEY = 'AIzaSy...'
+PATTERN_REGEX = '76115293'
+
+nextPageToken = ''
+pattern = re.compile(PATTERN_REGEX)
+
+def treatComment(comment):
+    id = comment['id']
+    textOriginal = comment['snippet']['textOriginal']
+    if pattern.match(textOriginal):
+        url = f'https://www.youtube.com/watch?v={VIDEO_ID}&lc={id}'
+        #os.system(f"firefox -new-tab '{url}'")
+        print(f'{url} {textOriginal}')
+
+while True:
+    data = getContentFromURL(f'commentThreads?part=snippet,replies&videoId={VIDEO_ID}&maxResults=100&pageToken={nextPageToken}')
+    #print(data)
+    for item in data['items']:
+        #print(item)
+        snippet = item['snippet']
+        totalReplyCount = snippet['totalReplyCount']
+        if totalReplyCount > 5:
+            parentId = item['id']
+            commentsNextPageToken = ''
+            while True:
+                commentsData = getContentFromURL(f'comments?part=snippet&parentId={parentId}&maxResults=100&pageToken={commentsNextPageToken}')
+                for item in commentsData['items']:
+                    treatComment(item)
+                if not 'nextPageToken' in commentsData:
+                    break
+                commentsNextPageToken = commentsData['nextPageToken']
+        else:
+            treatComment(snippet['topLevelComment'])
+            if totalReplyCount > 0:
+                for comment in item['replies']['comments']:
+                    treatComment(comment)
+    if not 'nextPageToken' in data:
+        break
+    nextPageToken = data['nextPageToken']
+