bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-12 21:28:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Updated test, test metadata

Browse Source
This commit is contained in:
erinhmclark
2025-02-06 10:11:56 +00:00
parent 52542812dc
commit 5b0bad832f
5 changed files with 284 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/auto_archiver/modules/gsheet_db/gsheet_db.py
View File

@@ -104,7 +104,6 @@ class GsheetsDb(Database):
if gsheet := item.get_context("gsheet"):
gw: GWorksheet = gsheet.get("worksheet")
row: int = gsheet.get("row")
# todo doesn't exist, should be passed from
elif self.sheet_id:
print(self.sheet_id)

59
src/auto_archiver/modules/gsheet_feeder/gsheet_feeder.py
View File

@@ -37,41 +37,48 @@ class GsheetsFeeder(Feeder):
def __iter__(self) -> Metadata:
sh = self.open_sheet()
for ii, wks in enumerate(sh.worksheets()):
if not self.should_process_sheet(wks.title):
logger.debug(f"SKIPPED worksheet '{wks.title}' due to allow/block rules")
for ii, worksheet in enumerate(sh.worksheets()):
if not self.should_process_sheet(worksheet.title):
logger.debug(f"SKIPPED worksheet '{worksheet.title}' due to allow/block rules")
continue
logger.info(f'Opening worksheet {ii=}: {wks.title=} header={self.header}')
gw = GWorksheet(wks, header_row=self.header, columns=self.columns)
logger.info(f'Opening worksheet {ii=}: {worksheet.title=} header={self.header}')
gw = GWorksheet(worksheet, header_row=self.header, columns=self.columns)
if len(missing_cols := self.missing_required_columns(gw)):
logger.warning(f"SKIPPED worksheet '{wks.title}' due to missing required column(s) for {missing_cols}")
continue
for row in range(1 + self.header, gw.count_rows() + 1):
url = gw.get_cell(row, 'url').strip()
if not len(url): continue
# process and yield metadata here:
yield from self._process_rows(gw)
logger.success(f'Finished worksheet {worksheet.title}')
original_status = gw.get_cell(row, 'status')
status = gw.get_cell(row, 'status', fresh=original_status in ['', None])
# TODO: custom status parser(?) aka should_retry_from_status
if status not in ['', None]: continue
def _process_rows(self, gw: GWorksheet) -> Metadata:
for row in range(1 + self.header, gw.count_rows() + 1):
url = gw.get_cell(row, 'url').strip()
if not len(url): continue
original_status = gw.get_cell(row, 'status')
status = gw.get_cell(row, 'status', fresh=original_status in ['', None])
# TODO: custom status parser(?) aka should_retry_from_status
if status not in ['', None]: continue
# All checks done - archival process starts here
m = Metadata().set_url(url)
if gw.get_cell_or_default(row, 'folder', "") is None:
folder = ''
else:
folder = slugify(gw.get_cell_or_default(row, 'folder', "").strip())
if len(folder) and self.use_sheet_names_in_stored_paths:
folder = os.path.join(folder, slugify(self.sheet), slugify(wks.title))
# All checks done - archival process starts here
m = Metadata().set_url(url)
self._set_context(m, gw, row)
yield m
m.set_context('folder', folder)
m.set_context('worksheet', {"row": row, "worksheet": gw})
yield m
def _set_context(self, m: Metadata, gw: GWorksheet, row: int) -> Metadata:
# TODO: Check folder value not being recognised
m.set_context("gsheet", {"row": row, "worksheet": gw})
if gw.get_cell_or_default(row, 'folder', "") is None:
folder = ''
else:
folder = slugify(gw.get_cell_or_default(row, 'folder', "").strip())
if len(folder):
if self.use_sheet_names_in_stored_paths:
m.set_context("folder", os.path.join(folder, slugify(self.sheet), slugify(gw.wks.title)))
else:
m.set_context("folder", folder)
logger.success(f'Finished worksheet {wks.title}')
def should_process_sheet(self, sheet_name: str) -> bool:
if len(self.allow_worksheets) and sheet_name not in self.allow_worksheets: