wiseflow/test
2025-01-05 18:12:36 +08:00
..
reports v0.3.6test update 2025-01-04 13:57:12 +08:00
craw4ai_fetching.py v0.3.6 release 2025-01-05 18:12:36 +08:00
crawlee_fetching.py v0.3.6 mockup 2025-01-04 23:36:18 +08:00
deep_scraper_test.py v0.3.6 mockup 2025-01-04 23:36:18 +08:00
get_info_test.py v0.3.6 mockup 2025-01-04 23:36:18 +08:00
get_visual_info_for_samples.py v0.3.6 release 2025-01-05 18:12:36 +08:00
prompts.py v0.3.6test update 2025-01-04 13:57:12 +08:00
README_EN.md v0.3.6 release 2025-01-05 18:12:36 +08:00
README.md v0.3.6 release 2025-01-05 18:12:36 +08:00

Test Script Documentation

Web Content Fetching and Parsing

craw4ai_fetching.py

python craw4ai_fetching.py -S 'url1,url2...'

HTML Content Parsing

deep_scraper_test.py

python deep_scraper_test.py -F 'json_file_path'

Visual Large Model Information Extraction

get_visual_info_for_samples.py

python get_visual_info_for_samples.py -F 'json_file_path'

Large Model Information Extraction Testing

get_info_test.py

- To create focus point descriptions for test tasks, refer to [reports/wiseflow_report_v036_bigbrother666/task0/focus_point.json](./reports/wiseflow_report_v036_bigbrother666/task0/focus_point.json)

- To modify the prompt for get_info, edit [prompts.py](./prompts.py)
python get_info_test.py -D 'sample dir'

Result Submission and Sharing

Wiseflow is an open source project aiming to create an "information crawling tool for everyone" through collective contributions!

At this stage, submitting test results is equivalent to submitting project code - you'll be accepted as a contributor and may even be invited to participate in commercial projects!

Test results should be submitted to the reports directory. Create a subdirectory for each test named {test_content}_{test_date}_{tester}, for example:

mkdir -p reports/wiseflow_report_v036_bigbrother666

Please submit all test samples and the original output results of the program run, and create a README.md file in the directory to record the test content, test date, tester, test models, conclusions, statistical tables, etc.

Finally, edit the reports/README.md file, add the directory name of the test result to the index, so that others can view it.