dataset-retrieval/retrieving-bluesky-datasets.ipynb: update

dataset-retrieval/retrieving-bluesky-datasets.ipynb

@@ -98,14 +98,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import re, random, time\n",
     "import pandas as pd\n",
     "import numpy as np\n",
-    "import re\n",
     "from tqdm import tqdm\n",
     "from more_itertools import chunked\n",
     "\n",
     "# Remove URLs, hashtags, mentions, emojis and whitespaces\n",
     "def clean_text(text):\n",
+    "    if not isinstance(text, str):\n",
+    "        return np.nan\n",
     "    text = re.sub(r'http\\S+|www\\S+|https\\S+', '', text, flags=re.MULTILINE)\n",
     "    text = re.sub(r'#\\S+', '', text)\n",
     "    text = re.sub(r'@\\S+', '', text)\n",
@@ -113,110 +115,163 @@
     "    text = re.sub(r'\\s+', ' ', text).strip()\n",
     "    return text\n",
     "\n",
-    "# Search for posts containing a specific keyword\n",
+    "# Retry helper\n",
-    "def get_posts_by_keyword(keyword, since, until, limit=300):\n",
+    "def call_with_retry(fn, *args, max_retries=5, base_delay=2, **kwargs):\n",
+    "    last_exc = None\n",
+    "    for attempt in range(1, max_retries + 1):\n",
     "        try:\n",
-    "        num_posts = 0\n",
+    "            return fn(*args, **kwargs)\n",
-    "        post_data = []\n",
+    "        except Exception as e:\n",
+    "            last_exc = e\n",
+    "            wait = base_delay * (2 ** (attempt - 1)) + random.uniform(0, 1)\n",
+    "            print(f' [retry {attempt}/{max_retries}] {type(e).__name__}: {e} - retrying in {wait:.1f}s')\n",
+    "            time.sleep(wait)\n",
+    "    raise last_exc\n",
     "\n",
-    "        progress_bar = tqdm(total=limit, desc=\"Fetching posts\")\n",
+    "# Post field extraction\n",
+    "def extract_post(post):\n",
+    "    try:\n",
+    "        text = clean_text(post.record.text) if hasattr(post.record, 'text') else None\n",
+    "        iso_date = post.record.created_at if hasattr(post.record, 'created_at') else None\n",
+    "        user = post.author.handle if hasattr(post.author, 'handle') else None\n",
+    "        post_id = post.uri if hasattr(post, 'uri') else None\n",
+    "        parent_id = (\n",
+    "            post.record.reply.parent.uri\n",
+    "            if hasattr(post.record, 'reply') and hasattr(post.record.reply, 'parent')\n",
+    "            else 'no_parent'\n",
+    "        )\n",
     " \n",
-    "        while num_posts < limit:\n",
+    "        if iso_date is None or post_id is None or user is None:\n",
+    "            return None\n",
     " \n",
-    "            search_results = client.app.bsky.feed.search_posts({'q': keyword, 'since': since, 'until': until, 'lang': 'en', 'limit': 100})\n",
-    "            posts = search_results.posts\n",
-    "\n",
-    "            for post in posts:\n",
-    "                        # Extract post details\n",
-    "                        text = clean_text(post.record.text) if hasattr(post.record, 'text') else np.nan\n",
-    "                        iso_date = post.record.created_at if hasattr(post.record, 'created_at') else np.nan\n",
-    "                        user = post.author.handle if hasattr(post.author, 'handle') else np.nan\n",
-    "\n",
-    "                        post_id = post.uri if hasattr(post, 'uri') else np.nan\n",
-    "                        parent_id = post.record.reply.parent.uri if hasattr(post.record, 'reply') and hasattr(post.record.reply, 'parent') else 'no_parent'\n",
-    "\n",
-    "                        # Format date-time\n",
-    "                        if iso_date != np.nan:\n",
     "        date_obj = datetime.fromisoformat(iso_date.replace('Z', '+00:00'))\n",
     "        date_str = date_obj.strftime('%Y-%m-%d %H:%M:%S')\n",
-    "                        else:\n",
-    "                            date_str = np.nan\n",
     " \n",
-    "                        if post_id != np.nan and user != np.nan:\n",
+    "        return {\n",
-    "                            post_data.append({\n",
     "            'date': date_str,\n",
-    "                                'text': text,\n",
+    "            'text': text if text is not None else np.nan,\n",
     "            'user': user,\n",
     "            'id': post_id,\n",
-    "                                'parentid': parent_id\n",
+    "            'parentid': parent_id,\n",
-    "                            })\n",
+    "        }, date_obj\n",
-    "                        else:\n",
+    "    except Exception as e:\n",
-    "                            continue\n",
+    "        print(f\"  Skipping malformed post: {e}\")\n",
+    "        return None\n",
     "\n",
-    "            until = iso_date\n",
+    "# Cleanup\n",
-    "            num_posts += len(posts)\n",
+    "def _dedupe(rows):\n",
-    "            progress_bar.update(len(posts))\n",
+    "    if not rows:\n",
-    "            progress_bar.set_postfix_str(f'now at: {date_str}')\n",
+    "        return pd.DataFrame()\n",
+    "    df = pd.DataFrame(rows)\n",
+    "    before = len(df)\n",
+    "    df = df.drop_duplicates(subset='id')\n",
+    "    df = df.dropna(subset=['text', 'id', 'user'])\n",
+    "    df = df[df['text'].astype(str).str.strip() != '']\n",
+    "    after = len(df)\n",
+    "    if before != after:\n",
+    "        print(f\"(Filtered {before - after} duplicate/empty rows out of {before}.)\")\n",
+    "    return df.reset_index(drop=True)\n",
     "\n",
-    "            if date_obj < (start_timestamp + timedelta(hours=1)):\n",
+    "        \n",
+    "# Search for posts containing a specific keyword\n",
+    "def get_posts_by_keyword(keyword, since, until, limit=300, page_size=100, max_retries=5):\n",
+    "\n",
+    "    state = _STATE.setdefault(keyword, {'until': until, 'rows': []})\n",
+    " \n",
+    "    if state['until'] != until and state['rows']:\n",
+    "        print(f\"Resuming '{keyword}' from until={state['until']}, {len(state['rows'])} posts already fetched this session.\")\n",
+    " \n",
+    "    since_dt = datetime.fromisoformat(since.replace('Z', '+00:00'))\n",
+    "    progress_bar = tqdm(total=limit, initial=min(len(state['rows']), limit), desc=\"Fetching posts\")\n",
+    "\n",
+    "    try:\n",
+    "        while len(state['rows']) < limit:\n",
+    "            try:\n",
+    "                search_results = call_with_retry(client.app.bsky.feed.search_posts, {'q': keyword, 'since': since, 'until': state['until'], 'lang': 'en', 'limit': page_size}, max_retries=max_retries)\n",
+    "            except Exception as e:\n",
+    "                print(f\"Giving up on this page after {max_retries} retries: {e}\")\n",
+    "                print(\"Progress so far is kept — just call this again to continue.\")\n",
     "                break\n",
     "    \n",
-    "        progress_bar.close()\n",
-    "        df = pd.DataFrame(post_data)\n",
-    "        return df\n",
-    "\n",
-    "    except Exception as e:\n",
-    "        print(f\"Error fetching posts: {e}\")\n",
-    "        return pd.DataFrame()\n",
-    "\n",
-    "# Obtain posts from uri list\n",
-    "def get_posts(uris):\n",
-    "    try:\n",
-    "        post_data = []\n",
-    "\n",
-    "        progress_bar = tqdm(total=len(uris), desc=\"Fetching posts\")\n",
-    "\n",
-    "        for uribit in list(chunked(uris,20)):\n",
-    "\n",
-    "            search_results = client.app.bsky.feed.get_posts({'uris': uribit})\n",
     "            posts = search_results.posts\n",
+    "            if not posts:\n",
+    "                print(\"No more posts returned — reached the end of available results.\")\n",
+    "                break\n",
     "    \n",
+    "            oldest_date_obj = None\n",
     "            for post in posts:\n",
-    "                # Extract post details\n",
+    "                result = extract_post(post)\n",
-    "                text = clean_text(post.record.text) if hasattr(post.record, 'text') else np.nan\n",
+    "                if result is None:\n",
-    "                iso_date = post.record.created_at if hasattr(post.record, 'created_at') else np.nan\n",
-    "                user = post.author.handle if hasattr(post.author, 'handle') else np.nan\n",
-    "\n",
-    "                post_id = post.uri if hasattr(post, 'uri') else np.nan\n",
-    "                parent_id = post.record.reply.parent.uri if hasattr(post.record, 'reply') and hasattr(post.record.reply, 'parent') else 'no_parent'\n",
-    "\n",
-    "                # Format date-time\n",
-    "                if iso_date != np.nan:\n",
-    "                    date_obj = datetime.fromisoformat(iso_date.replace('Z', '+00:00'))\n",
-    "                    date_str = date_obj.strftime('%Y-%m-%d %H:%M:%S')\n",
-    "                else:\n",
-    "                    date_str = np.nan\n",
-    "\n",
-    "                if post_id != np.nan and user != np.nan:\n",
-    "                    post_data.append({\n",
-    "                        'date': date_str,\n",
-    "                        'text': text,\n",
-    "                        'user': user,\n",
-    "                        'id': post_id,\n",
-    "                        'parentid': parent_id\n",
-    "                    })\n",
-    "                else:\n",
     "                    continue\n",
+    "                row, date_obj = result\n",
+    "                state['rows'].append(row)\n",
+    "                if oldest_date_obj is None or date_obj < oldest_date_obj:\n",
+    "                    oldest_date_obj = date_obj\n",
     "    \n",
     "            progress_bar.update(len(posts))\n",
     "    \n",
-    "        progress_bar.close()\n",
+    "            if oldest_date_obj is not None:\n",
-    "        df = pd.DataFrame(post_data)\n",
+    "                state['until'] = oldest_date_obj.isoformat().replace('+00:00', 'Z')\n",
-    "        return df\n",
+    "                progress_bar.set_postfix_str(f'now at: {state[\"until\"]}')\n",
     "    \n",
+    "                if oldest_date_obj < since_dt + timedelta(hours=1):\n",
+    "                    print(\"Reached the `since` boundary.\")\n",
+    "                    break\n",
+    " \n",
+    "    finally:\n",
+    "        progress_bar.close()\n",
+    " \n",
+    "    print(f\"{len(state['rows'])} posts fetched in total this session for '{keyword}'. Call again with the same checkpoint_name to keep going.\")\n",
+    "    return _dedupe(state['rows'])\n",
+    "\n",
+    "# Obtain posts from uri list\n",
+    "def get_posts(uris, chunk_size=20, max_retries=5):\n",
+    "    state = _STATE.setdefault('_by_uri', {'done_uris': set(), 'rows': []})\n",
+    " \n",
+    "    remaining = [u for u in uris if u not in state['done_uris']]\n",
+    "    chunks = list(chunked(remaining, chunk_size))\n",
+    " \n",
+    "    progress_bar = tqdm(total=len(uris), initial=len(state['done_uris']), desc=\"Fetching posts\")\n",
+    " \n",
+    "    try:\n",
+    "        for uribit in chunks:\n",
+    "            try:\n",
+    "                search_results = call_with_retry(client.app.bsky.feed.get_posts, {'uris': uribit}, max_retries=max_retries)\n",
     "            except Exception as e:\n",
-    "        print(f\"Error fetching posts: {e}\")\n",
+    "                print(f\"Skipping this chunk of {len(uribit)} URIs after {max_retries} retries: {e}\")\n",
-    "        return pd.DataFrame()"
+    "                continue\n",
+    " \n",
+    "            for post in search_results.posts:\n",
+    "                result = extract_post(post)\n",
+    "                if result is None:\n",
+    "                    continue\n",
+    "                row, _ = result\n",
+    "                state['rows'].append(row)\n",
+    " \n",
+    "            state['done_uris'].update(uribit)\n",
+    "            progress_bar.update(len(uribit))\n",
+    " \n",
+    "    finally:\n",
+    "        progress_bar.close()\n",
+    " \n",
+    "    print(f\"{len(state['done_uris'])}/{len(uris)} URIs processed in total.\")\n",
+    "    return _dedupe(state['rows'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Define state"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_STATE = {}"
    ]
   },
   {
@@ -233,7 +288,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "raw_df_data = get_posts_by_keyword('...', iso_start_timestamp, iso_end_timestamp, 500000)\n",
+    "raw_df_data = get_posts_by_keyword('...', iso_start_timestamp, iso_end_timestamp, 100000)\n",
     "raw_df_data.info()"
    ]
   },
@@ -251,13 +306,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "_STATE = {}\n",
     "id_list = raw_df_data['id'].to_list()\n",
     "id_list.append('no_parent')\n",
-    "\n",
+    "absent_parents = raw_df_data.loc[~raw_df_data['parentid'].isin(id_list), 'parentid'].tolist()"
-    "absent_parents = raw_df_data.loc[~raw_df_data['parentid'].isin(id_list), 'parentid'].tolist()\n",
+   ]
-    "\n",
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "df_absent_data = get_posts(absent_parents)\n",
-    "\n",
     "df_absent_data.info()"
    ]
   },
@@ -275,44 +336,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_data = pd.concat(raw_df_data, df_absent_data, ignore_index=True)\n",
+    "df_data = pd.concat([raw_df_data, df_absent_data], ignore_index=True)\n",
-    "\n",
-    "df_data.info()"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Drop duplicates."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df_data = df_data.drop_duplicates()\n",
-    "df_data.info()"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Remove empty entries."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df_data.dropna(inplace=True,subset=['text'])\n",
     "df_data.info()"
    ]
   },
@@ -356,7 +380,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_data.to_csv(f'../datasets/{case}.csv', index=False)"
+    "df_data.to_csv(f'{case}.csv', index=False)"
    ]
   },
   {
@@ -458,7 +482,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "closed_df_reduced_data.to_csv(f'../datasets/{case}-social-closed.csv', index=False)"
+    "closed_df_reduced_data.to_csv(f'{case}-social-closed.csv', index=False)"
    ]
   },
   {
@@ -475,7 +499,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "closed_df_data.to_csv(f'../datasets/{case}-closed.csv', index=False)"
+    "closed_df_data.to_csv(f'{case}-closed.csv', index=False)"
    ]
   }
  ],