Commit Graph

106 Commits

Author SHA1 Message Date
LawyZheng
31a79a1313 use value of the optiona when the content is empty (#4035) 2025-11-20 00:04:39 +08:00
LawyZheng
f6145665c8 mark readonly element as interactable (#3845) 2025-10-29 13:10:21 +08:00
pedrohsdb
5b80614aac Wait time optimization xp (#3802) 2025-10-23 16:09:42 -07:00
LawyZheng
55bc6bd367 helper function for wait animation (#3240) 2025-08-20 14:28:01 +08:00
LawyZheng
1588d8018b improve dynamic wait when multiple frames (#3228) 2025-08-19 14:09:03 +08:00
LawyZheng
9a359ebfde decrease parse input prompt token (#3210) 2025-08-16 10:05:38 +08:00
LawyZheng
654cdb14e4 fix wait for animation end (#3201) 2025-08-15 15:24:54 +08:00
LawyZheng
6b8d29a23d fix stop waiting bug (#3197) 2025-08-15 03:51:39 +08:00
LawyZheng
cac4792f38 remove hard waiting time in scraping (#3195) 2025-08-15 02:24:59 +08:00
Shuchang Zheng
52dc5a510b fix economy element tree trimming (#3182) 2025-08-13 21:45:14 -07:00
Shuchang Zheng
434bbff459 add support_empty_page and wait_seconds to the scrape_website interface (#3181) 2025-08-13 19:22:50 -07:00
devsy-bot[bot]
e3a3309e9c fix: change scraper log level from info to debug (#3143)
Co-authored-by: devsy-bot <no-reply@devsy.ai>
Co-authored-by: Claude <noreply@anthropic.com>
2025-08-08 08:56:30 -07:00
LawyZheng
ecc0e2e17d better failure reason for blank page (#3049)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-07-29 14:40:54 +08:00
LawyZheng
bff7544b83 fix scraping issue (#3035) 2025-07-25 12:53:22 +08:00
LawyZheng
fcd22017b7 make scraping timeout configurable (#2991) 2025-07-19 13:18:12 +08:00
Jonathan Dobson
f5d7639de8 allow empty urls (#2984) 2025-07-18 10:20:33 -04:00
Jonathan Dobson
c13c36f99e distinctify failed scrapes due to no url (#2977) 2025-07-17 16:19:16 -04:00
LawyZheng
95ab8295ce laminar integration (#2887) 2025-07-07 14:43:10 +08:00
Shuchang Zheng
cb17dbbb6f extend select agent to support date picker (#2849) 2025-07-01 13:12:39 +08:00
Asher Foa
effd0c4911 Add pyupgrade pre-commit hook + modernize python code (#2611) 2025-06-10 18:52:38 +00:00
Shuchang Zheng
47709dc0d8 support cross domain css sheet parse (#2535) 2025-05-30 09:51:59 +08:00
Shuchang Zheng
cf08ca951e Fix chrome user data dir problem (#2503) 2025-05-28 22:41:06 -07:00
Shuchang Zheng
31d6dbdacd stop removing target attr when scraping (#2495) 2025-05-28 15:55:01 +08:00
Shuchang Zheng
cca2772765 fix new tab a issue (#2437) 2025-05-23 13:18:42 +08:00
Shuchang Zheng
24a73b7af0 select option on click (#2391) 2025-05-20 00:08:55 +08:00
Shuchang Zheng
8b834436b5 anthropic support - dymanic window size / window popup (#2284) 2025-05-04 00:40:16 -07:00
Shuchang Zheng
a851e8fdd8 Reduce execution waits (#2282) 2025-05-04 00:30:09 -04:00
Shuchang Zheng
c69e5848ed add more scrape page methods (#2211) 2025-04-22 16:37:39 +08:00
Shuchang Zheng
f2eef5aa6d support shadow dom mutation observer (#2206)
Co-authored-by: lawyzheng <lawyzheng1106@gmail.com>
2025-04-21 22:36:56 +08:00
Shuchang Zheng
f883b91180 integration with CUA (#2126) 2025-04-11 11:18:53 -07:00
Shuchang Zheng
03d5383a42 fallback get incremental tree without waiting (#2118) 2025-04-10 02:36:27 +08:00
Shuchang Zheng
a72fcadd9a only take up to 1 screenshot if the html too big (#2108) 2025-04-05 23:33:34 -04:00
Shuchang Zheng
3c612968ce trim svg elements when prompt exceeds context window (#2106) 2025-04-04 22:33:52 -04:00
Shuchang Zheng
d8d8f8ab79 revert checkbox detect enhance (#1998) 2025-03-22 09:07:58 +08:00
Shuchang Zheng
4f9af0d797 fail task right away when scraping failed - no need to retry scraping failure at step level (#1997) 2025-03-21 15:47:36 -07:00
Shuchang Zheng
c680e33b30 don't drawbox when check user goal (#1964) 2025-03-19 02:06:09 +08:00
Shuchang Zheng
785c2f0626 add svg into interactable detecting (#1917) 2025-03-11 03:04:45 +08:00
Saurabh Misra
fcc87243c1 ️ Speed up function clean_element_before_hashing by 827% (#1890)
Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
2025-03-08 02:14:48 -08:00
Shuchang Zheng
9b9c84f7dc enhance checkbox detecting (#1840)
Co-authored-by: LawyZheng <lawyzheng1106@gmail.com>
2025-02-26 18:47:09 +08:00
Shuchang Zheng
30ae63bae9 pop frame_index from element for element hashing (#1785) 2025-02-18 16:45:17 +08:00
Shuchang Zheng
5e49685c76 refactor unique id generation (#1781) 2025-02-18 08:58:23 +08:00
Shuchang Zheng
defd761e58 add functionality to cache task_run (#1755) 2025-02-11 14:47:41 +08:00
Shuchang Zheng
6f3dcd13b8 fix invisible iframe scraping (#1723) 2025-02-05 13:33:45 +08:00
Shuchang Zheng
0fa11a484b improve selection dom listener performance (#1667) 2025-01-28 21:14:31 +08:00
Shuchang Zheng
f01502bdde optimize domutils (#1656) 2025-01-27 22:01:15 +08:00
Shuchang Zheng
ed4d0c59e7 speed up extraction (#1617) 2025-01-22 22:43:50 +08:00
Shuchang Zheng
34c3434885 shu/autoupgrade pre commit (#1553) 2025-01-14 14:06:43 -08:00
LawyZheng
d63061f13b fix search on auto completion (#1544) 2025-01-14 13:08:35 +08:00
LawyZheng
e10d9d46fb decrease the hash trigger to 150 (#1541) 2025-01-13 17:56:45 +08:00
LawyZheng
c6140fa405 fix selection issues (#1515) 2025-01-08 14:27:50 +08:00