firecrawl-sdk 1.17.0 → 1.17.1
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.
- checksums.yaml +4 -4
- data/README.md +9 -0
- data/lib/firecrawl/client.rb +9 -0
- data/lib/firecrawl/models/parse_format.rb +36 -0
- data/lib/firecrawl/version.rb +1 -1
- data/lib/firecrawl.rb +1 -0
- metadata +3 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: e2b500556e1d7b0d222ae8937ae86dccdcf8c6499871c0202608a46b4611ef17
|
|
4
|
+
data.tar.gz: 2e4913c995ed97d8b55f295ab6adb0e61fe42cc0f08aff1f8aa12763f765b2be
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: d138c5083321098460e7ab5777201300ba0b1701f93361e97a27e0b87c88c9bd3163e56124d9b2da94536855a99e41522d13002c73379d1c67dd7bfb280b9624
|
|
7
|
+
data.tar.gz: 64e7178e770554abd242289756c2de70fcd3d76d2104002e36c2d8773065aa14f1e4ca161b60a72ed063da9fb4f5fa1a050d49f79809fbedf951ce2d481909fe
|
data/README.md
CHANGED
|
@@ -126,6 +126,15 @@ doc = client.parse(file,
|
|
|
126
126
|
puts doc.markdown
|
|
127
127
|
```
|
|
128
128
|
|
|
129
|
+
List the file formats the parse endpoint accepts. `available` is `false` for
|
|
130
|
+
formats the deployment can't currently handle (e.g. images when OCR is off).
|
|
131
|
+
|
|
132
|
+
```ruby
|
|
133
|
+
client.get_parse_formats.each do |f|
|
|
134
|
+
puts "#{f.format} (#{f.kind}) #{f.extensions.join(", ")} #{f.mime_types.join(", ")} available=#{f.available}"
|
|
135
|
+
end
|
|
136
|
+
```
|
|
137
|
+
|
|
129
138
|
### Crawl
|
|
130
139
|
|
|
131
140
|
```ruby
|
data/lib/firecrawl/client.rb
CHANGED
|
@@ -195,6 +195,15 @@ module Firecrawl
|
|
|
195
195
|
Models::Document.new(data)
|
|
196
196
|
end
|
|
197
197
|
|
|
198
|
+
# Lists the file formats accepted by {#parse} on this deployment.
|
|
199
|
+
#
|
|
200
|
+
# @return [Array<Models::ParseFormat>]
|
|
201
|
+
def get_parse_formats
|
|
202
|
+
raw = @http.get("/v2/parse/formats")
|
|
203
|
+
formats = (raw["data"] || {})["formats"] || []
|
|
204
|
+
formats.map { |f| Models::ParseFormat.new(f) }
|
|
205
|
+
end
|
|
206
|
+
|
|
198
207
|
# ================================================================
|
|
199
208
|
# CRAWL
|
|
200
209
|
# ================================================================
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Firecrawl
|
|
4
|
+
module Models
|
|
5
|
+
# A file format accepted by the `/v2/parse` endpoint.
|
|
6
|
+
#
|
|
7
|
+
# `kind` is usually one of {KIND_DOCUMENT} or {KIND_IMAGE}, but newer API
|
|
8
|
+
# versions may return other values, which are kept as-is.
|
|
9
|
+
class ParseFormat
|
|
10
|
+
KIND_DOCUMENT = "document"
|
|
11
|
+
KIND_IMAGE = "image"
|
|
12
|
+
|
|
13
|
+
attr_reader :format, :kind, :extensions, :mime_types, :available
|
|
14
|
+
|
|
15
|
+
def initialize(data)
|
|
16
|
+
@format = data["format"]
|
|
17
|
+
@kind = data["kind"]
|
|
18
|
+
@extensions = data["extensions"] || []
|
|
19
|
+
@mime_types = data["mimeTypes"] || []
|
|
20
|
+
@available = data["available"]
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
def document?
|
|
24
|
+
kind == KIND_DOCUMENT
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
def image?
|
|
28
|
+
kind == KIND_IMAGE
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def to_s
|
|
32
|
+
"ParseFormat{format=#{format}, kind=#{kind}, available=#{available}}"
|
|
33
|
+
end
|
|
34
|
+
end
|
|
35
|
+
end
|
|
36
|
+
end
|
data/lib/firecrawl/version.rb
CHANGED
data/lib/firecrawl.rb
CHANGED
|
@@ -22,6 +22,7 @@ require_relative "firecrawl/models/search_options"
|
|
|
22
22
|
require_relative "firecrawl/models/search_data"
|
|
23
23
|
require_relative "firecrawl/models/parse_file"
|
|
24
24
|
require_relative "firecrawl/models/parse_options"
|
|
25
|
+
require_relative "firecrawl/models/parse_format"
|
|
25
26
|
require_relative "firecrawl/models/agent_options"
|
|
26
27
|
require_relative "firecrawl/models/agent_response"
|
|
27
28
|
require_relative "firecrawl/models/agent_list_response"
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: firecrawl-sdk
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.17.
|
|
4
|
+
version: 1.17.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Firecrawl
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-
|
|
11
|
+
date: 2026-10-02 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: A type-safe Ruby client for the Firecrawl v2 API. Supports scraping,
|
|
14
14
|
crawling, batch scraping, URL mapping, web search, and AI agent operations.
|
|
@@ -45,6 +45,7 @@ files:
|
|
|
45
45
|
- lib/firecrawl/models/menu_profile.rb
|
|
46
46
|
- lib/firecrawl/models/monitor.rb
|
|
47
47
|
- lib/firecrawl/models/parse_file.rb
|
|
48
|
+
- lib/firecrawl/models/parse_format.rb
|
|
48
49
|
- lib/firecrawl/models/parse_options.rb
|
|
49
50
|
- lib/firecrawl/models/pdf_parser.rb
|
|
50
51
|
- lib/firecrawl/models/product_profile.rb
|