crawlberg 1.0.1 → 1.0.3

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 3fef501414af0f060bbd74518d19f132b39b1b4ab48e517c26f8c4d588f1cbe7
4
- data.tar.gz: 2937571ed0798968eb0567df042837ff65a8603de68882017099b969045395a2
3
+ metadata.gz: 14f3cbbce5b53366e44498f012fe7b79b45b8a11a4c5cd712dfd4f5dcbd18934
4
+ data.tar.gz: c18b8a4575a244bd54fff1db81e1b21266a6a52d54cec99e7c760f1abad6f076
5
5
  SHA512:
6
- metadata.gz: d74f342935558ffadd242c187138704ae15b787f66262001ff9341c66e0ed05ad28ec83fad781f4d82af72ee3579f56dac643ed2e2a4f36960b7ac609ce432cd
7
- data.tar.gz: f3125487a1167bed9fc2b3b119bb50bc2419dc7cb8cc2678c0d676ab44a7ae5ca3ba0843041bbf6e8981d9305611b8fc512f250819e3c994463551a87655a795
6
+ metadata.gz: d0a381e2451d54f1e1a016d3d832df167f5aaee8fac4b0eb81631b32cebac8b8000bc6d3f5119d51b9f29a8a92c9b0707ed33aebdf76d7f97a3809dc1c5fb047
7
+ data.tar.gz: 40ff0204c26d0dc39c5b9161036cda1b91157f9e3a9d7e1ac06be03806c6322f68ebd43f5fd8357d1ee75f69d0682e89c702cdac32f25a59f4eb5a59f7dc37a7
@@ -145,9 +145,9 @@ checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
145
145
 
146
146
  [[package]]
147
147
  name = "aws-lc-rs"
148
- version = "1.17.0"
148
+ version = "1.17.1"
149
149
  source = "registry+https://github.com/rust-lang/crates.io-index"
150
- checksum = "5ec2f1fc3ec205783a5da9a7e6c1509cc69dedf09a1949e412c1e18469326d00"
150
+ checksum = "4342d8937fc7e5dd9b1c60292261c0670c882a2cd1719cfc11b1af41731e32ad"
151
151
  dependencies = [
152
152
  "aws-lc-sys",
153
153
  "zeroize",
@@ -155,14 +155,15 @@ dependencies = [
155
155
 
156
156
  [[package]]
157
157
  name = "aws-lc-sys"
158
- version = "0.41.0"
158
+ version = "0.42.0"
159
159
  source = "registry+https://github.com/rust-lang/crates.io-index"
160
- checksum = "1a2f9779ce85b93ab6170dd940ad0169b5766ff848247aff13bb788b832fe3f4"
160
+ checksum = "6d9ceb1da931507a12f4fccea479dccd00da1943e1b4ae72d8e502d707361444"
161
161
  dependencies = [
162
162
  "cc",
163
163
  "cmake",
164
164
  "dunce",
165
165
  "fs_extra",
166
+ "pkg-config",
166
167
  ]
167
168
 
168
169
  [[package]]
@@ -544,9 +545,9 @@ dependencies = [
544
545
 
545
546
  [[package]]
546
547
  name = "crawlberg"
547
- version = "1.0.1"
548
+ version = "1.0.3"
548
549
  source = "registry+https://github.com/rust-lang/crates.io-index"
549
- checksum = "3b29d0b66d3886745ab12e56e17a9127dc91f30b7261a2080c9eed67074c34f6"
550
+ checksum = "46b3f6dfec53e26f1f989b4685943153a54e1d2101f8bd3ae5afd810b7957423"
550
551
  dependencies = [
551
552
  "ahash",
552
553
  "aho-corasick",
@@ -586,7 +587,7 @@ dependencies = [
586
587
 
587
588
  [[package]]
588
589
  name = "crawlberg-rb"
589
- version = "1.0.0"
590
+ version = "1.0.3"
590
591
  dependencies = [
591
592
  "crawlberg",
592
593
  "futures",
@@ -1042,9 +1043,9 @@ dependencies = [
1042
1043
 
1043
1044
  [[package]]
1044
1045
  name = "html-to-markdown-rs"
1045
- version = "3.7.2"
1046
+ version = "3.8.0"
1046
1047
  source = "registry+https://github.com/rust-lang/crates.io-index"
1047
- checksum = "e80e5d74dbe02fc52264d6a1d21c12bbc0cb062bca64caa295e4703590f1aabe"
1048
+ checksum = "da9935e81a6fee38ebbc5a2ca4e9590f99f650ffb8a08734c4115a3e06c3c5d3"
1048
1049
  dependencies = [
1049
1050
  "ahash",
1050
1051
  "astral-tl",
@@ -1056,7 +1057,7 @@ dependencies = [
1056
1057
  "lru",
1057
1058
  "memchr",
1058
1059
  "once_cell",
1059
- "phf",
1060
+ "phf 0.14.0",
1060
1061
  "regex",
1061
1062
  "serde",
1062
1063
  "serde_json",
@@ -1765,9 +1766,19 @@ name = "phf"
1765
1766
  version = "0.13.1"
1766
1767
  source = "registry+https://github.com/rust-lang/crates.io-index"
1767
1768
  checksum = "c1562dc717473dbaa4c1f85a36410e03c047b2e7df7f45ee938fbef64ae7fadf"
1769
+ dependencies = [
1770
+ "phf_shared 0.13.1",
1771
+ "serde",
1772
+ ]
1773
+
1774
+ [[package]]
1775
+ name = "phf"
1776
+ version = "0.14.0"
1777
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1778
+ checksum = "010378780309880b08997fae13be7834dba947d36393bd372f2b1556deb2a2f6"
1768
1779
  dependencies = [
1769
1780
  "phf_macros",
1770
- "phf_shared",
1781
+ "phf_shared 0.14.0",
1771
1782
  "serde",
1772
1783
  ]
1773
1784
 
@@ -1777,8 +1788,8 @@ version = "0.13.1"
1777
1788
  source = "registry+https://github.com/rust-lang/crates.io-index"
1778
1789
  checksum = "49aa7f9d80421bca176ca8dbfebe668cc7a2684708594ec9f3c0db0805d5d6e1"
1779
1790
  dependencies = [
1780
- "phf_generator",
1781
- "phf_shared",
1791
+ "phf_generator 0.13.1",
1792
+ "phf_shared 0.13.1",
1782
1793
  ]
1783
1794
 
1784
1795
  [[package]]
@@ -1788,17 +1799,27 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
1788
1799
  checksum = "135ace3a761e564ec88c03a77317a7c6b80bb7f7135ef2544dbe054243b89737"
1789
1800
  dependencies = [
1790
1801
  "fastrand",
1791
- "phf_shared",
1802
+ "phf_shared 0.13.1",
1803
+ ]
1804
+
1805
+ [[package]]
1806
+ name = "phf_generator"
1807
+ version = "0.14.0"
1808
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1809
+ checksum = "aeb62e0959d5a1bebc965f4d15d9e2b7cea002b6b0f5ba8cde6cc26738467100"
1810
+ dependencies = [
1811
+ "fastrand",
1812
+ "phf_shared 0.14.0",
1792
1813
  ]
1793
1814
 
1794
1815
  [[package]]
1795
1816
  name = "phf_macros"
1796
- version = "0.13.1"
1817
+ version = "0.14.0"
1797
1818
  source = "registry+https://github.com/rust-lang/crates.io-index"
1798
- checksum = "812f032b54b1e759ccd5f8b6677695d5268c588701effba24601f6932f8269ef"
1819
+ checksum = "5fa8d0ca26d424d27630da600c6624696e7dec8bf7b3b492b383c5dc49e5e085"
1799
1820
  dependencies = [
1800
- "phf_generator",
1801
- "phf_shared",
1821
+ "phf_generator 0.14.0",
1822
+ "phf_shared 0.14.0",
1802
1823
  "proc-macro2",
1803
1824
  "quote",
1804
1825
  "syn",
@@ -1813,12 +1834,27 @@ dependencies = [
1813
1834
  "siphasher",
1814
1835
  ]
1815
1836
 
1837
+ [[package]]
1838
+ name = "phf_shared"
1839
+ version = "0.14.0"
1840
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1841
+ checksum = "c6fd9027e2d9319be6349febd1db4e8d02aa544921200c9b777720ac34a3aa89"
1842
+ dependencies = [
1843
+ "siphasher",
1844
+ ]
1845
+
1816
1846
  [[package]]
1817
1847
  name = "pin-project-lite"
1818
1848
  version = "0.2.17"
1819
1849
  source = "registry+https://github.com/rust-lang/crates.io-index"
1820
1850
  checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
1821
1851
 
1852
+ [[package]]
1853
+ name = "pkg-config"
1854
+ version = "0.3.33"
1855
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1856
+ checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e"
1857
+
1822
1858
  [[package]]
1823
1859
  name = "png"
1824
1860
  version = "0.18.1"
@@ -1901,9 +1937,9 @@ checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
1901
1937
 
1902
1938
  [[package]]
1903
1939
  name = "quick-xml"
1904
- version = "0.40.1"
1940
+ version = "0.41.0"
1905
1941
  source = "registry+https://github.com/rust-lang/crates.io-index"
1906
- checksum = "2474bd2e5029e7ccb6abb2ba48cf2383a333851dedf495901544281590c7da7f"
1942
+ checksum = "e660451e55124f798a69a5af3f49ccfbefbd41910eefd25caf2393e1f3473ec1"
1907
1943
  dependencies = [
1908
1944
  "memchr",
1909
1945
  ]
@@ -2149,9 +2185,9 @@ dependencies = [
2149
2185
 
2150
2186
  [[package]]
2151
2187
  name = "rustc-hash"
2152
- version = "2.1.2"
2188
+ version = "2.1.3"
2153
2189
  source = "registry+https://github.com/rust-lang/crates.io-index"
2154
- checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
2190
+ checksum = "6b1e7f9a428571be2dc5bc0505c13fb6bf936822b894ec87abf8a08a4e51742d"
2155
2191
 
2156
2192
  [[package]]
2157
2193
  name = "rustc_version"
@@ -2190,9 +2226,9 @@ dependencies = [
2190
2226
 
2191
2227
  [[package]]
2192
2228
  name = "rustls-pki-types"
2193
- version = "1.14.1"
2229
+ version = "1.15.0"
2194
2230
  source = "registry+https://github.com/rust-lang/crates.io-index"
2195
- checksum = "30a7197ae7eb376e574fe940d068c30fe0462554a3ddbe4eca7838e049c937a9"
2231
+ checksum = "764899a24af3980067ee14bc143654f297b22eaebfe3c7b6b211920a5a59b046"
2196
2232
  dependencies = [
2197
2233
  "web-time",
2198
2234
  "zeroize",
@@ -2468,7 +2504,7 @@ checksum = "a18596f8c785a729f2819c0f6a7eae6ebeebdfffbfe4214ae6b087f690e31901"
2468
2504
  dependencies = [
2469
2505
  "new_debug_unreachable",
2470
2506
  "parking_lot",
2471
- "phf_shared",
2507
+ "phf_shared 0.13.1",
2472
2508
  "precomputed-hash",
2473
2509
  ]
2474
2510
 
@@ -2478,8 +2514,8 @@ version = "0.6.1"
2478
2514
  source = "registry+https://github.com/rust-lang/crates.io-index"
2479
2515
  checksum = "585635e46db231059f76c5849798146164652513eb9e8ab2685939dd90f29b69"
2480
2516
  dependencies = [
2481
- "phf_generator",
2482
- "phf_shared",
2517
+ "phf_generator 0.13.1",
2518
+ "phf_shared 0.13.1",
2483
2519
  "proc-macro2",
2484
2520
  "quote",
2485
2521
  ]
@@ -2574,9 +2610,9 @@ dependencies = [
2574
2610
 
2575
2611
  [[package]]
2576
2612
  name = "time"
2577
- version = "0.3.51"
2613
+ version = "0.3.53"
2578
2614
  source = "registry+https://github.com/rust-lang/crates.io-index"
2579
- checksum = "85c17d80feb7334b40c484e45ed1a5273dfd8bfda537c3be2e74a06a6686f327"
2615
+ checksum = "18dfaaeddcb932337b5e7866ee7d0ce9b76d2fd092997146f187ec09b4558a50"
2580
2616
  dependencies = [
2581
2617
  "deranged",
2582
2618
  "num-conv",
@@ -2594,9 +2630,9 @@ checksum = "9e1c906769ad99c88eaa54e728060edef082f8e358ff32030cb7c7d315e81109"
2594
2630
 
2595
2631
  [[package]]
2596
2632
  name = "time-macros"
2597
- version = "0.2.30"
2633
+ version = "0.2.31"
2598
2634
  source = "registry+https://github.com/rust-lang/crates.io-index"
2599
- checksum = "dcef1a61bdb119096e153208ec5cbec23944ce8bca13be5c7f60c634f7403935"
2635
+ checksum = "c431b87111666e491a90baa837f914fb45cd5dc3c268591b0220ff5057f2085f"
2600
2636
  dependencies = [
2601
2637
  "num-conv",
2602
2638
  "time-core",
@@ -3011,7 +3047,7 @@ version = "0.2.5"
3011
3047
  source = "registry+https://github.com/rust-lang/crates.io-index"
3012
3048
  checksum = "075474b12bcb3d2e3d4546580e9de478eeeead668a1761e2a8860c836b7ef297"
3013
3049
  dependencies = [
3014
- "phf",
3050
+ "phf 0.13.1",
3015
3051
  "phf_codegen",
3016
3052
  "string_cache",
3017
3053
  "string_cache_codegen",
@@ -1,6 +1,6 @@
1
1
  [package]
2
2
  name = "crawlberg-rb"
3
- version = "1.0.0"
3
+ version = "1.0.3"
4
4
  edition = "2024"
5
5
  license = "MIT"
6
6
  description = "High-performance web crawling engine"
@@ -17,7 +17,7 @@ path = "../src/lib.rs"
17
17
  crate-type = ["cdylib"]
18
18
 
19
19
  [dependencies]
20
- crawlberg = { version = "1.0.1", features = ["interact", "browser-chromiumoxide"] }
20
+ crawlberg = { version = "1.0.3", features = ["interact", "browser-chromiumoxide"] }
21
21
  futures = "0.3"
22
22
  magnus = "0.8"
23
23
  rb-sys = ">=0.9, <0.9.128"
@@ -1,5 +1,5 @@
1
1
  // This file is auto-generated by alef. DO NOT EDIT.
2
- // alef:hash:06831f8166c6d860691af36ee02b72ae3246568eb2e5c67ed5d11da71d02afeb
2
+ // alef:hash:e0600612767fdd3d51e9128afdb0ffcd1fb490e9942f3839a5120ab7a4e3b658
3
3
  // Re-generate with: alef generate
4
4
  #![allow(dead_code, unused_imports, unused_variables)]
5
5
  #![allow(
@@ -438,21 +438,7 @@ unsafe impl TryConvertOwned for BrowserConfig {}
438
438
 
439
439
  impl Default for BrowserConfig {
440
440
  fn default() -> Self {
441
- Self {
442
- mode: BrowserMode::Auto,
443
- backend: BrowserBackend::Chromiumoxide,
444
- endpoint: None,
445
- timeout: 30000,
446
- wait: Default::default(),
447
- wait_selector: None,
448
- extra_wait: None,
449
- proxy: None,
450
- block_url_patterns: vec![],
451
- eval_script: None,
452
- robots_user_agent: None,
453
- capture_network_events: false,
454
- session_affinity: true,
455
- }
441
+ crawlberg::BrowserConfig::default().into()
456
442
  }
457
443
  }
458
444
 
@@ -641,47 +627,7 @@ unsafe impl TryConvertOwned for CrawlConfig {}
641
627
 
642
628
  impl Default for CrawlConfig {
643
629
  fn default() -> Self {
644
- Self {
645
- max_depth: None,
646
- max_pages: None,
647
- max_concurrent: None,
648
- respect_robots_txt: false,
649
- soft_http_errors: false,
650
- user_agent: None,
651
- stay_on_domain: false,
652
- allow_subdomains: false,
653
- include_paths: vec![],
654
- exclude_paths: vec![],
655
- custom_headers: Default::default(),
656
- request_timeout: 30000,
657
- rate_limit_ms: None,
658
- max_redirects: 10,
659
- retry_count: 0,
660
- retry_codes: vec![],
661
- cookies_enabled: false,
662
- auth: None,
663
- max_body_size: None,
664
- remove_tags: vec![],
665
- content: Default::default(),
666
- map_limit: None,
667
- map_search: None,
668
- download_assets: false,
669
- asset_types: vec![],
670
- max_asset_size: None,
671
- browser: Default::default(),
672
- proxy: None,
673
- user_agents: vec![],
674
- capture_screenshot: false,
675
- follow_document_urls: false,
676
- document_url_depth: None,
677
- download_documents: true,
678
- document_max_size: None,
679
- document_mime_types: vec![],
680
- warc_output: None,
681
- browser_profile: None,
682
- save_browser_profile: false,
683
- ssrf: Default::default(),
684
- }
630
+ crawlberg::CrawlConfig::default().into()
685
631
  }
686
632
  }
687
633
 
@@ -2410,13 +2356,7 @@ unsafe impl TryConvertOwned for LinkInfo {}
2410
2356
 
2411
2357
  impl Default for LinkInfo {
2412
2358
  fn default() -> Self {
2413
- Self {
2414
- url: String::new(),
2415
- text: String::new(),
2416
- link_type: Default::default(),
2417
- rel: None,
2418
- nofollow: false,
2419
- }
2359
+ crawlberg::LinkInfo::default().into()
2420
2360
  }
2421
2361
  }
2422
2362
 
@@ -2511,13 +2451,7 @@ unsafe impl TryConvertOwned for ImageInfo {}
2511
2451
 
2512
2452
  impl Default for ImageInfo {
2513
2453
  fn default() -> Self {
2514
- Self {
2515
- url: String::new(),
2516
- alt: None,
2517
- width: None,
2518
- height: None,
2519
- source: Default::default(),
2520
- }
2454
+ crawlberg::ImageInfo::default().into()
2521
2455
  }
2522
2456
  }
2523
2457
 
@@ -2608,11 +2542,7 @@ unsafe impl TryConvertOwned for FeedInfo {}
2608
2542
 
2609
2543
  impl Default for FeedInfo {
2610
2544
  fn default() -> Self {
2611
- Self {
2612
- url: String::new(),
2613
- title: None,
2614
- feed_type: Default::default(),
2615
- }
2545
+ crawlberg::FeedInfo::default().into()
2616
2546
  }
2617
2547
  }
2618
2548
 
@@ -2854,14 +2784,7 @@ unsafe impl TryConvertOwned for DownloadedAsset {}
2854
2784
 
2855
2785
  impl Default for DownloadedAsset {
2856
2786
  fn default() -> Self {
2857
- Self {
2858
- url: String::new(),
2859
- content_hash: String::new(),
2860
- mime_type: None,
2861
- size: 0,
2862
- asset_category: Default::default(),
2863
- html_tag: None,
2864
- }
2787
+ crawlberg::DownloadedAsset::default().into()
2865
2788
  }
2866
2789
  }
2867
2790
 
@@ -6556,9 +6479,15 @@ impl From<crawlberg::BrowserBackend> for BrowserBackend {
6556
6479
  impl From<AuthConfig> for crawlberg::AuthConfig {
6557
6480
  fn from(val: AuthConfig) -> Self {
6558
6481
  match val {
6559
- AuthConfig::Basic { username, password } => Self::Basic { username, password },
6560
- AuthConfig::Bearer { token } => Self::Bearer { token },
6561
- AuthConfig::Header { name, value } => Self::Header { name, value },
6482
+ AuthConfig::Basic { username, password } => Self::Basic {
6483
+ username: username,
6484
+ password: password,
6485
+ },
6486
+ AuthConfig::Bearer { token } => Self::Bearer { token: token },
6487
+ AuthConfig::Header { name, value } => Self::Header {
6488
+ name: name,
6489
+ value: value,
6490
+ },
6562
6491
  }
6563
6492
  }
6564
6493
  }
@@ -6689,7 +6618,9 @@ impl From<crawlberg::CrawlEvent> for CrawlEvent {
6689
6618
  url: url.to_string(),
6690
6619
  error: error.to_string(),
6691
6620
  },
6692
- crawlberg::CrawlEvent::Complete { pages_crawled } => Self::Complete { pages_crawled },
6621
+ crawlberg::CrawlEvent::Complete { pages_crawled } => Self::Complete {
6622
+ pages_crawled: pages_crawled,
6623
+ },
6693
6624
  }
6694
6625
  }
6695
6626
  }
@@ -6697,21 +6628,27 @@ impl From<crawlberg::CrawlEvent> for CrawlEvent {
6697
6628
  impl From<PageAction> for crawlberg::PageAction {
6698
6629
  fn from(val: PageAction) -> Self {
6699
6630
  match val {
6700
- PageAction::Click { selector } => Self::Click { selector },
6701
- PageAction::TypeText { selector, text } => Self::TypeText { selector, text },
6702
- PageAction::Press { key } => Self::Press { key },
6631
+ PageAction::Click { selector } => Self::Click { selector: selector },
6632
+ PageAction::TypeText { selector, text } => Self::TypeText {
6633
+ selector: selector,
6634
+ text: text,
6635
+ },
6636
+ PageAction::Press { key } => Self::Press { key: key },
6703
6637
  PageAction::Scroll {
6704
6638
  direction,
6705
6639
  selector,
6706
6640
  amount,
6707
6641
  } => Self::Scroll {
6708
6642
  direction: direction.into(),
6709
- selector,
6710
- amount,
6643
+ selector: selector,
6644
+ amount: amount,
6711
6645
  },
6712
- PageAction::Wait { milliseconds, selector } => Self::Wait { milliseconds, selector },
6713
- PageAction::Screenshot { full_page } => Self::Screenshot { full_page },
6714
- PageAction::ExecuteJs { script } => Self::ExecuteJs { script },
6646
+ PageAction::Wait { milliseconds, selector } => Self::Wait {
6647
+ milliseconds: milliseconds,
6648
+ selector: selector,
6649
+ },
6650
+ PageAction::Screenshot { full_page } => Self::Screenshot { full_page: full_page },
6651
+ PageAction::ExecuteJs { script } => Self::ExecuteJs { script: script },
6715
6652
  PageAction::Scrape => Self::Scrape,
6716
6653
  }
6717
6654
  }
@@ -6735,13 +6672,13 @@ impl From<crawlberg::PageAction> for PageAction {
6735
6672
  } => Self::Scroll {
6736
6673
  direction: direction.into(),
6737
6674
  selector: selector.map(|v| v.to_string()),
6738
- amount,
6675
+ amount: amount,
6739
6676
  },
6740
6677
  crawlberg::PageAction::Wait { milliseconds, selector } => Self::Wait {
6741
- milliseconds,
6678
+ milliseconds: milliseconds,
6742
6679
  selector: selector.map(|v| v.to_string()),
6743
6680
  },
6744
- crawlberg::PageAction::Screenshot { full_page } => Self::Screenshot { full_page },
6681
+ crawlberg::PageAction::Screenshot { full_page } => Self::Screenshot { full_page: full_page },
6745
6682
  crawlberg::PageAction::ExecuteJs { script } => Self::ExecuteJs {
6746
6683
  script: script.to_string(),
6747
6684
  },