@zenrows/cli 1.7.0 → 1.8.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (16) hide show
  1. package/README.md +64 -9
  2. package/agent-plugin/skills/batch-jobs/SKILL.md +16 -3
  3. package/dist/src/adapters/batch.js +237 -59
  4. package/dist/src/cli/commands/batch.js +665 -126
  5. package/dist/src/cli/commands/crawl.js +1 -1
  6. package/dist/src/core/batch-api.js +398 -145
  7. package/dist/src/core/config.js +1 -1
  8. package/dist/src/core/errors.js +6 -0
  9. package/dist/src/core/policy.js +13 -6
  10. package/package.json +1 -1
  11. package/recipes/batch-estimate/RECIPE.md +6 -3
  12. package/skills/batch-jobs/SKILL.md +160 -43
  13. package/skills/crawl/SKILL.md +1 -1
  14. package/skills/trace-debug/SKILL.md +17 -2
  15. package/skills/zenrows/SKILL.md +3 -2
  16. package/templates/batch-jsonl-pipeline/README.md +10 -5
package/dist/src/cli/commands/crawl.js CHANGED
@@ -34,7 +34,7 @@ export const crawl = {
34
34
  " leave it out for no depth limit (the caps below stop the crawl)",
35
35
  " --max-items <n> stop after keeping n URLs (API default 100)",
36
36
  " --max-pages <n> stop after fetching n pages (API default 100; bounds cost);",
37
- " the local policy max_pages_per_run caps it (default 1000)",
37
+ " the local policy max_pages_per_run caps it (default 10000)",
38
38
  " --include-patterns <p> keep only URLs containing this substring (repeatable)",
39
39
  " --exclude-patterns <p> drop URLs containing this substring (repeatable)",
40
40
  " --output-format <html|markdown> also fetch each kept URL's page, as HTML or Markdown",