pagesift-api 0.61.0

Firecrawl v2 compatible HTTP API for pagesift.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233

//! Firecrawl v1/v2 response types and metadata structures.

use serde::{Deserialize, Serialize};
use serde_json::Value;
use std::collections::BTreeMap;

/// Explanation when a query-directed crawl completes (`pagesift` field in job status).
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct CrawlSummary {
    /// `coverage_reached`, `saturated`, `limit_reached`, `exhausted`, `cancelled`.
    pub stop_reason: String,
    /// Coverage percentage (0.0 to 1.0) when adaptive crawl completes.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub coverage: Option<f64>,
    /// Number of distinct evidence blocks gathered for each term.
    #[serde(skip_serializing_if = "BTreeMap::is_empty", default)]
    pub term_evidence: BTreeMap<String, usize>,
    /// Actual pages fetched.
    pub pages: usize,
}

/// PageSift extensions inside `metadata.pagesift`.
#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct PagesiftMeta {
    #[serde(skip_serializing_if = "Option::is_none")]
    pub content_hash: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub raw_hash: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub text_hash: Option<String>,
    #[serde(skip_serializing_if = "Vec::is_empty", default)]
    pub redirect_chain: Vec<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub etag: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub last_modified: Option<String>,
    #[serde(skip_serializing_if = "std::ops::Not::not", default)]
    pub not_modified: bool,
    /// `http` or `browser`.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub engine: Option<String>,
    /// `lightpanda`, `moli`, or `chrome`.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub browser_engine: Option<String>,
    #[serde(skip_serializing_if = "Vec::is_empty", default)]
    pub warnings: Vec<String>,
    /// Timing per phase in milliseconds.
    #[serde(skip_serializing_if = "BTreeMap::is_empty", default)]
    pub timings: BTreeMap<String, f64>,
    /// Duplicate canonical reference URL.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub duplicate_of: Option<String>,
    /// Query relevance score (0.0 to 1.0).
    #[serde(skip_serializing_if = "Option::is_none")]
    pub relevance: Option<f32>,
    /// Query filter statistics.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub query_filter: Option<QueryFilterStats>,
}

#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct QueryFilterStats {
    pub kept_blocks: usize,
    pub total_blocks: usize,
    pub tokens_before: usize,
    pub tokens_after: usize,
}

/// Firecrawl `changeTracking` response object.
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct ChangeTracking {
    pub previous_scrape_at: Option<String>,
    /// `new`, `same`, `changed`, `removed`.
    pub change_status: String,
    /// `visible` or `hidden`.
    pub visibility: String,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub diff: Option<Value>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub json: Option<Value>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub pagesift: Option<Value>,
}

#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct Metadata {
    #[serde(skip_serializing_if = "Option::is_none")]
    pub title: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub description: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub language: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub keywords: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub robots: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub favicon: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub published_time: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub author: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub modified_time: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub url: Option<String>,
    #[serde(rename = "sourceURL", skip_serializing_if = "Option::is_none")]
    pub source_url: Option<String>,
    pub status_code: u16,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub content_type: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub error: Option<String>,
    pub proxy_used: String,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub cache_state: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub cached_at: Option<String>,
    #[serde(flatten)]
    pub extra: BTreeMap<String, Value>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub pagesift: Option<PagesiftMeta>,
}

#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct Document {
    #[serde(skip_serializing_if = "Option::is_none")]
    pub markdown: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub html: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub raw_html: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub links: Option<Vec<String>>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub images: Option<Vec<String>>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub screenshot: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub json: Option<Value>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub summary: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub actions: Option<Value>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub warning: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub change_tracking: Option<ChangeTracking>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub chunks: Option<Vec<DocChunk>>,
    pub metadata: Metadata,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct DocChunk {
    pub text: String,
    pub heading_path: Vec<String>,
    pub start: usize,
    pub end: usize,
    pub tokens: usize,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct MapLink {
    pub url: String,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub title: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub description: Option<String>,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct ScrapeResponse {
    pub success: bool,
    pub data: Document,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub warning: Option<String>,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct JobStarted {
    pub success: bool,
    pub id: String,
    pub url: String,
    #[serde(rename = "invalidURLs", skip_serializing_if = "Option::is_none")]
    pub invalid_urls: Option<Vec<String>>,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct JobStatus {
    pub success: bool,
    pub status: String,
    pub completed: usize,
    pub total: usize,
    pub credits_used: usize,
    pub expires_at: String,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub next: Option<String>,
    pub data: Vec<Document>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub pagesift: Option<CrawlSummary>,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct JobError {
    pub id: String,
    pub timestamp: String,
    pub url: String,
    pub code: String,
    pub error: String,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct JobErrors {
    pub errors: Vec<JobError>,
    pub robots_blocked: Vec<String>,
}

#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct MapResponse {
    pub success: bool,
    pub links: Vec<MapLink>,
}