cleanup auto_archive and config

Pipfile

@@ -6,7 +6,6 @@ name = "pypi"
 [packages]
 gspread = "*"
 boto3 = "*"
-python-dotenv = "*"
 argparse = "*"
 beautifulsoup4 = "*"
 tiktok-downloader = {git = "https://github.com/msramalho/tiktok-downloader"}

Pipfile.lock

@@ -707,14 +707,6 @@
             "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
             "version": "==2.8.2"
         },
-        "python-dotenv": {
-            "hashes": [
-                "sha256:b7e3b04a59693c42c36f9ab1cc2acc46fa5df8c78e178fc33a8d4cd05c8d498f",
-                "sha256:d92a187be61fe482e4fd675b6d52200e7be63a12b724abbf931a40ce4fa92938"
-            ],
-            "index": "pypi",
-            "version": "==0.20.0"
-        },
         "requests": {
             "hashes": [
                 "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61",

archivers/wayback_archiver.py

@@ -78,6 +78,6 @@ class WaybackArchiver(Archiver):
             title = "Could not get title"
 
         screenshot = self.get_screenshot(url)
-        result = ArchiveResult(status='Internet Archive fallback', cdn_url=archive_url, title=title, screenshot=screenshot)
+        result = ArchiveResult(status='success', cdn_url=archive_url, title=title, screenshot=screenshot)
         self.seen_urls[url] = result
         return result

auto_archive.py

@@ -1,24 +1,12 @@
-import sys
 import datetime
 import shutil
-from loguru import logger
-from dotenv import load_dotenv
-
 import traceback
+from loguru import logger
 
 from archivers import TelethonArchiver, TelegramArchiver, TiktokArchiver, YoutubeDLArchiver, TwitterArchiver, WaybackArchiver, ArchiveResult
 from utils import GWorksheet, mkdir_if_not_exists, expand_url
 from configs import Config
 
-from storages.gd_storage import GDConfig, GDStorage
-from utils import GWorksheet, mkdir_if_not_exists
-import sys
-
-logger.add("logs/1trace.log", level="TRACE")
-logger.add("logs/2info.log", level="INFO")
-logger.add("logs/3success.log", level="SUCCESS")
-logger.add("logs/4warning.log", level="WARNING")
-logger.add("logs/5error.log", level="ERROR")
 
 def update_sheet(gw, row, result: ArchiveResult):
     cell_updates = []
@@ -33,8 +21,7 @@ def update_sheet(gw, row, result: ArchiveResult):
 
     batch_if_valid('archive', result.cdn_url)
     batch_if_valid('date', True, datetime.datetime.utcnow().replace(tzinfo=datetime.timezone.utc).isoformat())
-    batch_if_valid('thumbnail', result.thumbnail,
-                   f'=IMAGE("{result.thumbnail}")')
+    batch_if_valid('thumbnail', result.thumbnail, f'=IMAGE("{result.thumbnail}")')
     batch_if_valid('thumbnail_index', result.thumbnail_index)
     batch_if_valid('title', result.title)
     batch_if_valid('duration', result.duration, str(result.duration))
@@ -54,109 +41,82 @@ def update_sheet(gw, row, result: ArchiveResult):
     gw.batch_set_cell(cell_updates)
 
 
-def process_sheet(c: Config, sheet, header=1, columns=GWorksheet.COLUMN_NAMES):
-    sh = c.gsheets_client.open(sheet)
+def missing_required_columns(gw: GWorksheet):
+    required_found = True
+    for required_col in ['url', 'status']:
+        if not gw.col_exists(required_col):
+            logger.warning(f'Required column for {required_col}: "{gw.columns[required_col]}" not found, skipping worksheet {gw.worksheet.title}')
+            required_found = False
+    return required_found
+
+
+def process_sheet(c: Config):
+    sh = c.gsheets_client.open(c.sheet)
 
     # loop through worksheets to check
     for ii, wks in enumerate(sh.worksheets()):
-        logger.info(f'Opening worksheet {ii=}: {wks.title=} {header=}')
-        gw = GWorksheet(wks, header_row=header, columns=columns)
+        logger.info(f'Opening worksheet {ii=}: {wks.title=} {c.header=}')
+        gw = GWorksheet(wks, header_row=c.header, columns=c.column_names)
 
-        if not gw.col_exists('url'):
-            logger.warning(
-                f'No "{c.column_names["url"]}" column found, skipping worksheet {wks.title}')
-            continue
-
-        if not gw.col_exists('status'):
-            logger.warning(
-                f'No "{c.column_names["status"]}" column found, skipping worksheet {wks.title}')
-            continue
+        if missing_required_columns(gw): continue
 
         # archives will be in a folder 'doc_name/worksheet_name'
-        c.set_folder(f'{sheet.replace(" ", "_")}/{wks.title.replace(" ", "_")}/')
+        # TODO: use slugify lib
+        c.set_folder(f'{c.sheet.replace(" ", "_")}/{wks.title.replace(" ", "_")}/')
         storage = c.get_storage()
 
         # loop through rows in worksheet
-        for row in range(1 + header, gw.count_rows() + 1):
+        for row in range(1 + c.header, gw.count_rows() + 1):
             url = gw.get_cell(row, 'url')
             original_status = gw.get_cell(row, 'status')
             status = gw.get_cell(row, 'status', fresh=original_status in ['', None] and url != '')
 
-            if url != '' and status in ['', None]:
-                gw.set_cell(row, 'status', 'Archive in progress')
+            if url == '' or status not in ['', None]: continue
 
-                url = expand_url(url)
+            # All checks done - archival process starts here
+            gw.set_cell(row, 'status', 'Archive in progress')
+            url = expand_url(url)
+            storage.update_properties(subfolder=gw.get_cell_or_default(row, 'subfolder'))
 
-                subfolder = gw.get_cell_or_default(row, 'subfolder')
+            # make a new driver so each spreadsheet row is idempotent
+            c.recreate_webdriver()
 
-                # make a new driver so each spreadsheet row is idempotent
-                c.recreate_webdriver()
+            # order matters, first to succeed excludes remaining
+            active_archivers = [
+                TelethonArchiver(storage, c.webdriver, c.telegram_config),
+                TelegramArchiver(storage, c.webdriver),
+                TiktokArchiver(storage, c.webdriver),
+                YoutubeDLArchiver(storage, c.webdriver, c.facebook_cookie),
+                TwitterArchiver(storage, c.webdriver),
+                WaybackArchiver(storage, c.webdriver, c.wayback_config)
+            ]
 
-                # order matters, first to succeed excludes remaining
-                active_archivers = [
-                    TelethonArchiver(storage, c.webdriver, c.telegram_config),
-                    TelegramArchiver(storage, c.webdriver),
-                    TiktokArchiver(storage, c.webdriver),
-                    YoutubeDLArchiver(storage, c.webdriver, c.facebook_cookie),
-                    TwitterArchiver(storage, c.webdriver),
-                    WaybackArchiver(storage, c.webdriver, c.wayback_config)
-                ]
+            for archiver in active_archivers:
+                logger.debug(f'Trying {archiver=} on {row=}')
 
-                storage_client = None
-                if storage == "s3":
-                    storage_client = s3_client
-                elif storage == "gd":
-                    storage_client = gd_client
-                else:
-                    raise ValueError(f'Cant get storage_client {storage_client}')
-                storage_client.update_properties(subfolder=subfolder)
-                for archiver in active_archivers:
-                    logger.debug(f'Trying {archiver} on row {row}')
+                try:
+                    result = archiver.download(url, check_if_exists=True)
+                except KeyboardInterrupt:
+                    # catches keyboard interruptions to do a clean exit
+                    logger.warning(f"caught interrupt for {archiver=} on {row=}")
+                    gw.set_cell(row, 'status', '')
+                    c.destroy_webdriver()
+                    exit()
+                except Exception as e:
+                    result = False
+                    logger.error(f'Got unexpected error in row {row} with {archiver=} for {url=}: {e}\n{traceback.format_exc()}')
 
-                    try:
-                        result = archiver.download(url, check_if_exists=True)
-                    except KeyboardInterrupt:
-                        logger.warning("caught interrupt")
-                        gw.set_cell(row, 'status', '')
-                        driver.quit()
-                        exit()
-                    except Exception as e:
-                        result = False
-                        logger.error(f'Got unexpected error in row {row} with archiver {archiver} for url {url}: {e}\n{traceback.format_exc()}')
-
-                    if result:
-                        # IA is a Success I believe - or do we want to display a logger warning for it?
-                        if result.status in ['success', 'already archived', 'Internet Archive fallback']:
-                            result.status = archiver.name + \
-                                ": " + str(result.status)
-                            logger.success(
-                                f'{archiver} succeeded on row {row}, url {url}')
-                        if result.status in ['success', 'already archived']:
-                            result.status = f"{archiver.name}: {result.status}"
-                            logger.success(f'{archiver} succeeded on row {row}')
-                            break
-                        logger.warning(f'{archiver} did not succeed on row {row}, final status: {result.status}')
-                        result.status = f"{archiver.name}: {result.status}"
-
-
-                        # wayback has seen this url before so keep existing status
-                        if "wayback: Internet Archive fallback" in result.status:
-                            logger.success(
-                                f'wayback has seen this url before so keep existing status on row {row}')
-                            result.status = result.status.replace(' (duplicate)', '')
-                            result.status = str(result.status) + " (duplicate)"
-                            break
-
-                        logger.warning(
-                            f'{archiver} did not succeed on {row=}, final status: {result.status}')
-                        result.status = archiver.name + \
-                            ": " + str(result.status)
-                # get rid of driver so can reload on next row
-                driver.quit()
                 if result:
-                    update_sheet(gw, row, result)
-                else:
-                    gw.set_cell(row, 'status', 'failed: no archiver')
+                    result.status = f"{archiver.name}: {result.status}"
+                    if result.status in ['success', 'already archived']:
+                        logger.success(f'{archiver=} succeeded on {row=}, {url=}')
+                        break
+                    logger.warning(f'{archiver} did not succeed on {row=}, final status: {result.status}')
+
+            if result:
+                update_sheet(gw, row, result)
+            else:
+                gw.set_cell(row, 'status', 'failed: no archiver')
         logger.success(f'Finshed worksheet {wks.title}')
 
 
@@ -164,26 +124,11 @@ def process_sheet(c: Config, sheet, header=1, columns=GWorksheet.COLUMN_NAMES):
 def main():
     c = Config()
     c.parse()
-
     logger.info(f'Opening document {c.sheet} for header {c.header}')
-    parser.add_argument('--storage', action='store', dest='storage', default='s3', help='which storage to use.', choices={"s3", "gd"})
-
-    for k, v in GWorksheet.COLUMN_NAMES.items():
-        help = f"the name of the column to fill with {k} (defaults={v})"
-        if k == "subfolder":
-            help = f"the name of the column to read the {k} from (defaults={v})"
-        parser.add_argument(f'--col-{k}', action='store', dest=k, default=v, help=help)
-
     mkdir_if_not_exists(c.tmp_folder)
-    process_sheet(c, c.sheet, header=c.header, columns=c.column_names)
-    shutil.rmtree(c.tmp_folder)
+    process_sheet(c)
     c.destroy_webdriver()
-
-    logger.info(f'Opening document {args.sheet} for header {args.header}')
-
-    mkdir_if_not_exists('tmp')
-    process_sheet(args.sheet, header=args.header, columns=config_columns)
-    shutil.rmtree('tmp')
+    shutil.rmtree(c.tmp_folder)
 
 
 if __name__ == '__main__':

configs/config.py

@@ -37,6 +37,14 @@ class Config:
     def __init__(self):
         self.parser = self.get_argument_parser()
         self.folder = ""
+        self.set_log_files()
+
+    def set_log_files(self):
+        logger.add("logs/1trace.log", level="TRACE")
+        logger.add("logs/2info.log", level="INFO")
+        logger.add("logs/3success.log", level="SUCCESS")
+        logger.add("logs/4warning.log", level="WARNING")
+        logger.add("logs/5error.log", level="ERROR")
 
     def parse(self):
         self.args = self.parser.parse_args()
@@ -145,7 +153,10 @@ class Config:
         parser.add_argument('--s3-private', action='store_true', help='Store content without public access permission (only for storage=s3) [secrets.s3.private in config.json]')
 
         for k, v in GWorksheet.COLUMN_NAMES.items():
-            parser.add_argument(f'--col-{k}', action='store', dest=k, help=f"name of the column to fill with {k} (default='{v}')")
+            help = f"the name of the column to FILL WITH {k} (default='{v}')"
+            if k in ["url", "subfolder"]:
+                help = f"the name of the column to READ {k} FROM (default='{v}')"
+            parser.add_argument(f'--col-{k}', action='store', dest=k, help=help)
 
         return parser
 

utils/misc.py

@@ -13,7 +13,8 @@ def expand_url(url):
     if 'https://t.co/' in url:
         try:
             r = requests.get(url)
-            url = r.url
+            logger.debug(f'Expanded url {url} to {r.url}')
+            return r.url
         except:
             logger.error(f'Failed to expand url {url}')
     return url