diff options
Diffstat (limited to 'parsers/logbooks.py')
| -rw-r--r-- | parsers/logbooks.py | 9 |
1 files changed, 3 insertions, 6 deletions
diff --git a/parsers/logbooks.py b/parsers/logbooks.py index 0a3443a..4ebfe0a 100644 --- a/parsers/logbooks.py +++ b/parsers/logbooks.py @@ -26,17 +26,14 @@ Parses and imports logbooks in all their wonderful confusion todo=''' - Put the object store 'trips' and the 'logdataissues' into TROG global object -- works parsing logbooks but when reading cache files fails on storing data - and is slower than parsing from scratch now! +- Use the .shelve.db cache for all logbooks, not just individually - refactor everything with some urgency, esp. LoadLogbookForExpedition() -- far too many uses of Django field dereferencing to get values, which is SLOW -- Logbooks log.htm exist for 1983, 84, 85, 87, 88, 89 but have no full-working parser, - or it is broken/incomplete and need hand-editing. -- Loogbooks 1987, 1988, 1989 all crash on MySql - but not sqlite - with db constraint fail +- Loogbooks 1987, 1988, 1989 all crash on MySql - but not sqlite - with db constraint fail. Edit logbook to fix. - import/parse/re-export-as-html the 'artisanal-format' old logbooks so that we keep only a modern HTML05 format. Then we can retiure the old parsers and reduce the @@ -303,7 +300,7 @@ def Parseloghtmltxt(year, expedition, txt): for trippara in tripparas: logbook_entry_count += 1 tid = set_trip_id(year,logbook_entry_count) - print(f' - new tid:{tid} lbe count: {logbook_entry_count}') + # print(f' - new tid:{tid} lbe count: {logbook_entry_count}') s = re.match(r'''(?x)(?:\s*<div\sclass="tripdate"\sid=".*?">.*?</div>\s*<p>)? # second date \s*(?:<a\s+id="(.*?)"\s*/>\s*</a>)? |