Add README.md and search_in_youtube_video_comments.py

README.md

@@ -0,0 +1 @@
+# Search in YouTube video comments

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']
+