<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `src/result/crawler.rs`."><title>crawler.rs - source</title><script>if(window.location.protocol!=="file:")document.head.insertAdjacentHTML("beforeend","SourceSerif4-Regular-6b053e98.ttf.woff2,FiraSans-Italic-81dc35de.woff2,FiraSans-Regular-0fe48ade.woff2,FiraSans-MediumItalic-ccf7e434.woff2,FiraSans-Medium-e1aa3f0a.woff2,SourceCodePro-Regular-8badfe75.ttf.woff2,SourceCodePro-Semibold-aa29a496.ttf.woff2".split(",").map(f=>`<link rel="preload" as="font" type="font/woff2"href="../../../static.files/${f}">`).join(""))</script><link rel="stylesheet" href="../../../static.files/normalize-9960930a.css"><link rel="stylesheet" href="../../../static.files/rustdoc-b7b9f40b.css"><meta name="rustdoc-vars" data-root-path="../../../" data-static-root-path="../../../static.files/" data-current-crate="scrapfly_sdk" data-themes="" data-resource-suffix="" data-rustdoc-version="1.95.0 (59807616e 2026-04-14)" data-channel="1.95.0" data-search-js="search-63369b7b.js" data-stringdex-js="stringdex-b897f86f.js" data-settings-js="settings-170eb4bf.js" ><script src="../../../static.files/storage-41dd4d93.js"></script><script defer src="../../../static.files/src-script-813739b1.js"></script><script defer src="../../../src-files.js"></script><script defer src="../../../static.files/main-5013f961.js"></script><noscript><link rel="stylesheet" href="../../../static.files/noscript-f7c3ffd8.css"></noscript><link rel="alternate icon" type="image/png" href="../../../static.files/favicon-32x32-eab170b8.png"><link rel="icon" type="image/svg+xml" href="../../../static.files/favicon-044be391.svg"></head><body class="rustdoc src"><a class="skip-main-content" href="#main-content">Skip to main content</a><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><div class="src-sidebar-title"><h2>Files</h2></div></nav><div class="sidebar-resizer" title="Drag to resize sidebar"></div><main><section id="main-content" class="content" tabindex="-1"><div class="main-heading"><h1><div class="sub-heading">scrapfly_sdk/result/</div>crawler.rs</h1><rustdoc-toolbar></rustdoc-toolbar></div><div class="example-wrap digits-3"><pre class="rust"><code><a href=#1 id=1 data-nosnippet>1</a><span class="doccomment">//! Crawler result objects — port of `sdk/go/result_crawler.go`.
<a href=#2 id=2 data-nosnippet>2</a>
<a href=#3 id=3 data-nosnippet>3</a></span><span class="kw">use </span>std::collections::BTreeMap;
<a href=#4 id=4 data-nosnippet>4</a>
<a href=#5 id=5 data-nosnippet>5</a><span class="kw">use </span>bytes::Bytes;
<a href=#6 id=6 data-nosnippet>6</a><span class="kw">use </span>serde::Deserialize;
<a href=#7 id=7 data-nosnippet>7</a>
<a href=#8 id=8 data-nosnippet>8</a><span class="doccomment">/// Crawler status constants.
<a href=#9 id=9 data-nosnippet>9</a></span><span class="kw">pub mod </span>status {
<a href=#10 id=10 data-nosnippet>10</a> <span class="doccomment">/// Pending — not yet picked up.
<a href=#11 id=11 data-nosnippet>11</a> </span><span class="kw">pub const </span>PENDING: <span class="kw-2">&</span>str = <span class="string">"PENDING"</span>;
<a href=#12 id=12 data-nosnippet>12</a> <span class="doccomment">/// Running.
<a href=#13 id=13 data-nosnippet>13</a> </span><span class="kw">pub const </span>RUNNING: <span class="kw-2">&</span>str = <span class="string">"RUNNING"</span>;
<a href=#14 id=14 data-nosnippet>14</a> <span class="doccomment">/// Done (check `is_success` for success/failure).
<a href=#15 id=15 data-nosnippet>15</a> </span><span class="kw">pub const </span>DONE: <span class="kw-2">&</span>str = <span class="string">"DONE"</span>;
<a href=#16 id=16 data-nosnippet>16</a> <span class="doccomment">/// Cancelled by the user.
<a href=#17 id=17 data-nosnippet>17</a> </span><span class="kw">pub const </span>CANCELLED: <span class="kw-2">&</span>str = <span class="string">"CANCELLED"</span>;
<a href=#18 id=18 data-nosnippet>18</a>}
<a href=#19 id=19 data-nosnippet>19</a>
<a href=#20 id=20 data-nosnippet>20</a><span class="doccomment">/// Response from `POST /crawl`.
<a href=#21 id=21 data-nosnippet>21</a></span><span class="attr">#[derive(Debug, Clone, Deserialize, Default)]
<a href=#22 id=22 data-nosnippet>22</a></span><span class="kw">pub struct </span>CrawlerStartResponse {
<a href=#23 id=23 data-nosnippet>23</a> <span class="doccomment">/// Crawler job UUID.
<a href=#24 id=24 data-nosnippet>24</a> </span><span class="attr">#[serde(default)]
<a href=#25 id=25 data-nosnippet>25</a> </span><span class="kw">pub </span>crawler_uuid: String,
<a href=#26 id=26 data-nosnippet>26</a> <span class="doccomment">/// Initial status.
<a href=#27 id=27 data-nosnippet>27</a> </span><span class="attr">#[serde(default)]
<a href=#28 id=28 data-nosnippet>28</a> </span><span class="kw">pub </span>status: String,
<a href=#29 id=29 data-nosnippet>29</a>}
<a href=#30 id=30 data-nosnippet>30</a>
<a href=#31 id=31 data-nosnippet>31</a><span class="doccomment">/// Inner `state` block of [`CrawlerStatus`].
<a href=#32 id=32 data-nosnippet>32</a></span><span class="attr">#[derive(Debug, Clone, Deserialize, Default)]
<a href=#33 id=33 data-nosnippet>33</a></span><span class="kw">pub struct </span>CrawlerState {
<a href=#34 id=34 data-nosnippet>34</a> <span class="doccomment">/// URLs visited.
<a href=#35 id=35 data-nosnippet>35</a> </span><span class="attr">#[serde(default)]
<a href=#36 id=36 data-nosnippet>36</a> </span><span class="kw">pub </span>urls_visited: u64,
<a href=#37 id=37 data-nosnippet>37</a> <span class="doccomment">/// URLs extracted.
<a href=#38 id=38 data-nosnippet>38</a> </span><span class="attr">#[serde(default)]
<a href=#39 id=39 data-nosnippet>39</a> </span><span class="kw">pub </span>urls_extracted: u64,
<a href=#40 id=40 data-nosnippet>40</a> <span class="doccomment">/// URLs failed.
<a href=#41 id=41 data-nosnippet>41</a> </span><span class="attr">#[serde(default)]
<a href=#42 id=42 data-nosnippet>42</a> </span><span class="kw">pub </span>urls_failed: u64,
<a href=#43 id=43 data-nosnippet>43</a> <span class="doccomment">/// URLs skipped.
<a href=#44 id=44 data-nosnippet>44</a> </span><span class="attr">#[serde(default)]
<a href=#45 id=45 data-nosnippet>45</a> </span><span class="kw">pub </span>urls_skipped: u64,
<a href=#46 id=46 data-nosnippet>46</a> <span class="doccomment">/// URLs queued.
<a href=#47 id=47 data-nosnippet>47</a> </span><span class="attr">#[serde(default)]
<a href=#48 id=48 data-nosnippet>48</a> </span><span class="kw">pub </span>urls_to_crawl: u64,
<a href=#49 id=49 data-nosnippet>49</a> <span class="doccomment">/// API credit used.
<a href=#50 id=50 data-nosnippet>50</a> </span><span class="attr">#[serde(default)]
<a href=#51 id=51 data-nosnippet>51</a> </span><span class="kw">pub </span>api_credit_used: u64,
<a href=#52 id=52 data-nosnippet>52</a> <span class="doccomment">/// Duration (seconds).
<a href=#53 id=53 data-nosnippet>53</a> </span><span class="attr">#[serde(default)]
<a href=#54 id=54 data-nosnippet>54</a> </span><span class="kw">pub </span>duration: u64,
<a href=#55 id=55 data-nosnippet>55</a> <span class="doccomment">/// Start time (Unix seconds, null while PENDING).
<a href=#56 id=56 data-nosnippet>56</a> </span><span class="attr">#[serde(default)]
<a href=#57 id=57 data-nosnippet>57</a> </span><span class="kw">pub </span>start_time: <span class="prelude-ty">Option</span><i64>,
<a href=#58 id=58 data-nosnippet>58</a> <span class="doccomment">/// Stop time (Unix seconds, null until terminal).
<a href=#59 id=59 data-nosnippet>59</a> </span><span class="attr">#[serde(default)]
<a href=#60 id=60 data-nosnippet>60</a> </span><span class="kw">pub </span>stop_time: <span class="prelude-ty">Option</span><i64>,
<a href=#61 id=61 data-nosnippet>61</a> <span class="doccomment">/// Documented stop reason (null while running).
<a href=#62 id=62 data-nosnippet>62</a> </span><span class="attr">#[serde(default)]
<a href=#63 id=63 data-nosnippet>63</a> </span><span class="kw">pub </span>stop_reason: <span class="prelude-ty">Option</span><String>,
<a href=#64 id=64 data-nosnippet>64</a>}
<a href=#65 id=65 data-nosnippet>65</a>
<a href=#66 id=66 data-nosnippet>66</a><span class="doccomment">/// Response from `GET /crawl/{uuid}/status`.
<a href=#67 id=67 data-nosnippet>67</a></span><span class="attr">#[derive(Debug, Clone, Deserialize, Default)]
<a href=#68 id=68 data-nosnippet>68</a></span><span class="kw">pub struct </span>CrawlerStatus {
<a href=#69 id=69 data-nosnippet>69</a> <span class="doccomment">/// Crawler UUID.
<a href=#70 id=70 data-nosnippet>70</a> </span><span class="attr">#[serde(default)]
<a href=#71 id=71 data-nosnippet>71</a> </span><span class="kw">pub </span>crawler_uuid: String,
<a href=#72 id=72 data-nosnippet>72</a> <span class="doccomment">/// Status enum (`PENDING`, `RUNNING`, `DONE`, `CANCELLED`).
<a href=#73 id=73 data-nosnippet>73</a> </span><span class="attr">#[serde(default)]
<a href=#74 id=74 data-nosnippet>74</a> </span><span class="kw">pub </span>status: String,
<a href=#75 id=75 data-nosnippet>75</a> <span class="doccomment">/// Whether the crawler reached a terminal state.
<a href=#76 id=76 data-nosnippet>76</a> </span><span class="attr">#[serde(default)]
<a href=#77 id=77 data-nosnippet>77</a> </span><span class="kw">pub </span>is_finished: bool,
<a href=#78 id=78 data-nosnippet>78</a> <span class="doccomment">/// Success marker (nullable while running).
<a href=#79 id=79 data-nosnippet>79</a> </span><span class="attr">#[serde(default)]
<a href=#80 id=80 data-nosnippet>80</a> </span><span class="kw">pub </span>is_success: <span class="prelude-ty">Option</span><bool>,
<a href=#81 id=81 data-nosnippet>81</a> <span class="doccomment">/// Per-job metrics.
<a href=#82 id=82 data-nosnippet>82</a> </span><span class="attr">#[serde(default)]
<a href=#83 id=83 data-nosnippet>83</a> </span><span class="kw">pub </span>state: CrawlerState,
<a href=#84 id=84 data-nosnippet>84</a>}
<a href=#85 id=85 data-nosnippet>85</a>
<a href=#86 id=86 data-nosnippet>86</a><span class="kw">impl </span>CrawlerStatus {
<a href=#87 id=87 data-nosnippet>87</a> <span class="doccomment">/// True while still pending or running.
<a href=#88 id=88 data-nosnippet>88</a> </span><span class="kw">pub fn </span>is_running(<span class="kw-2">&</span><span class="self">self</span>) -> bool {
<a href=#89 id=89 data-nosnippet>89</a> <span class="self">self</span>.status == status::PENDING || <span class="self">self</span>.status == status::RUNNING
<a href=#90 id=90 data-nosnippet>90</a> }
<a href=#91 id=91 data-nosnippet>91</a> <span class="doccomment">/// True when terminated successfully.
<a href=#92 id=92 data-nosnippet>92</a> </span><span class="kw">pub fn </span>is_complete(<span class="kw-2">&</span><span class="self">self</span>) -> bool {
<a href=#93 id=93 data-nosnippet>93</a> <span class="self">self</span>.status == status::DONE && <span class="self">self</span>.is_success == <span class="prelude-val">Some</span>(<span class="bool-val">true</span>)
<a href=#94 id=94 data-nosnippet>94</a> }
<a href=#95 id=95 data-nosnippet>95</a> <span class="doccomment">/// True when terminated with failure.
<a href=#96 id=96 data-nosnippet>96</a> </span><span class="kw">pub fn </span>is_failed(<span class="kw-2">&</span><span class="self">self</span>) -> bool {
<a href=#97 id=97 data-nosnippet>97</a> <span class="self">self</span>.status == status::DONE && <span class="self">self</span>.is_success == <span class="prelude-val">Some</span>(<span class="bool-val">false</span>)
<a href=#98 id=98 data-nosnippet>98</a> }
<a href=#99 id=99 data-nosnippet>99</a> <span class="doccomment">/// True when cancelled by the user.
<a href=#100 id=100 data-nosnippet>100</a> </span><span class="kw">pub fn </span>is_cancelled(<span class="kw-2">&</span><span class="self">self</span>) -> bool {
<a href=#101 id=101 data-nosnippet>101</a> <span class="self">self</span>.status == status::CANCELLED
<a href=#102 id=102 data-nosnippet>102</a> }
<a href=#103 id=103 data-nosnippet>103</a>}
<a href=#104 id=104 data-nosnippet>104</a>
<a href=#105 id=105 data-nosnippet>105</a><span class="doccomment">/// One entry in the streaming `urls` list.
<a href=#106 id=106 data-nosnippet>106</a></span><span class="attr">#[derive(Debug, Clone)]
<a href=#107 id=107 data-nosnippet>107</a></span><span class="kw">pub struct </span>CrawlerUrlEntry {
<a href=#108 id=108 data-nosnippet>108</a> <span class="doccomment">/// URL.
<a href=#109 id=109 data-nosnippet>109</a> </span><span class="kw">pub </span>url: String,
<a href=#110 id=110 data-nosnippet>110</a> <span class="doccomment">/// Status (visited/pending/failed/skipped) — echoed from the request.
<a href=#111 id=111 data-nosnippet>111</a> </span><span class="kw">pub </span>status: String,
<a href=#112 id=112 data-nosnippet>112</a> <span class="doccomment">/// Reason for failure/skip (only set for `failed`/`skipped`).
<a href=#113 id=113 data-nosnippet>113</a> </span><span class="kw">pub </span>reason: String,
<a href=#114 id=114 data-nosnippet>114</a>}
<a href=#115 id=115 data-nosnippet>115</a>
<a href=#116 id=116 data-nosnippet>116</a><span class="doccomment">/// Streaming response from `GET /crawl/{uuid}/urls`.
<a href=#117 id=117 data-nosnippet>117</a></span><span class="attr">#[derive(Debug, Clone, Default)]
<a href=#118 id=118 data-nosnippet>118</a></span><span class="kw">pub struct </span>CrawlerUrls {
<a href=#119 id=119 data-nosnippet>119</a> <span class="doccomment">/// URL entries on this page.
<a href=#120 id=120 data-nosnippet>120</a> </span><span class="kw">pub </span>urls: Vec<CrawlerUrlEntry>,
<a href=#121 id=121 data-nosnippet>121</a> <span class="doccomment">/// Page number.
<a href=#122 id=122 data-nosnippet>122</a> </span><span class="kw">pub </span>page: u32,
<a href=#123 id=123 data-nosnippet>123</a> <span class="doccomment">/// Page size.
<a href=#124 id=124 data-nosnippet>124</a> </span><span class="kw">pub </span>per_page: u32,
<a href=#125 id=125 data-nosnippet>125</a>}
<a href=#126 id=126 data-nosnippet>126</a>
<a href=#127 id=127 data-nosnippet>127</a><span class="kw">impl </span>CrawlerUrls {
<a href=#128 id=128 data-nosnippet>128</a> <span class="doccomment">/// Parse a `text/plain` body into a [`CrawlerUrls`]. Mirrors
<a href=#129 id=129 data-nosnippet>129</a> /// `sdk/go/result_crawler.go::parseCrawlerURLs`.
<a href=#130 id=130 data-nosnippet>130</a> </span><span class="kw">pub fn </span>from_text(body: <span class="kw-2">&</span>str, status_hint: <span class="kw-2">&</span>str, page: u32, per_page: u32) -> <span class="self">Self </span>{
<a href=#131 id=131 data-nosnippet>131</a> <span class="kw">let </span><span class="kw-2">mut </span>urls = Vec::new();
<a href=#132 id=132 data-nosnippet>132</a> <span class="kw">for </span>raw_line <span class="kw">in </span>body.split(<span class="string">'\n'</span>) {
<a href=#133 id=133 data-nosnippet>133</a> <span class="kw">let </span>line = raw_line.trim();
<a href=#134 id=134 data-nosnippet>134</a> <span class="kw">if </span>line.is_empty() {
<a href=#135 id=135 data-nosnippet>135</a> <span class="kw">continue</span>;
<a href=#136 id=136 data-nosnippet>136</a> }
<a href=#137 id=137 data-nosnippet>137</a> <span class="kw">if </span>status_hint == <span class="string">"visited" </span>|| status_hint == <span class="string">"pending" </span>{
<a href=#138 id=138 data-nosnippet>138</a> urls.push(CrawlerUrlEntry {
<a href=#139 id=139 data-nosnippet>139</a> url: line.to_string(),
<a href=#140 id=140 data-nosnippet>140</a> status: status_hint.to_string(),
<a href=#141 id=141 data-nosnippet>141</a> reason: String::new(),
<a href=#142 id=142 data-nosnippet>142</a> });
<a href=#143 id=143 data-nosnippet>143</a> <span class="kw">continue</span>;
<a href=#144 id=144 data-nosnippet>144</a> }
<a href=#145 id=145 data-nosnippet>145</a> <span class="kw">if let </span><span class="prelude-val">Some</span>(idx) = line.find(<span class="string">','</span>) {
<a href=#146 id=146 data-nosnippet>146</a> urls.push(CrawlerUrlEntry {
<a href=#147 id=147 data-nosnippet>147</a> url: line[..idx].to_string(),
<a href=#148 id=148 data-nosnippet>148</a> status: status_hint.to_string(),
<a href=#149 id=149 data-nosnippet>149</a> reason: line[idx + <span class="number">1</span>..].to_string(),
<a href=#150 id=150 data-nosnippet>150</a> });
<a href=#151 id=151 data-nosnippet>151</a> } <span class="kw">else </span>{
<a href=#152 id=152 data-nosnippet>152</a> urls.push(CrawlerUrlEntry {
<a href=#153 id=153 data-nosnippet>153</a> url: line.to_string(),
<a href=#154 id=154 data-nosnippet>154</a> status: status_hint.to_string(),
<a href=#155 id=155 data-nosnippet>155</a> reason: String::new(),
<a href=#156 id=156 data-nosnippet>156</a> });
<a href=#157 id=157 data-nosnippet>157</a> }
<a href=#158 id=158 data-nosnippet>158</a> }
<a href=#159 id=159 data-nosnippet>159</a> <span class="self">Self </span>{
<a href=#160 id=160 data-nosnippet>160</a> urls,
<a href=#161 id=161 data-nosnippet>161</a> page,
<a href=#162 id=162 data-nosnippet>162</a> per_page,
<a href=#163 id=163 data-nosnippet>163</a> }
<a href=#164 id=164 data-nosnippet>164</a> }
<a href=#165 id=165 data-nosnippet>165</a>}
<a href=#166 id=166 data-nosnippet>166</a>
<a href=#167 id=167 data-nosnippet>167</a><span class="doccomment">/// `GET /crawl/{uuid}/contents` bulk-JSON envelope.
<a href=#168 id=168 data-nosnippet>168</a></span><span class="attr">#[derive(Debug, Clone, Deserialize, Default)]
<a href=#169 id=169 data-nosnippet>169</a></span><span class="kw">pub struct </span>CrawlerContents {
<a href=#170 id=170 data-nosnippet>170</a> <span class="doccomment">/// `url → format → content`. The API can emit `null` for a format that
<a href=#171 id=171 data-nosnippet>171</a> /// couldn't be produced for a given URL (e.g. `extracted_data` on a page
<a href=#172 id=172 data-nosnippet>172</a> /// that no template matched); the SDK flattens `null → ""` so consumers
<a href=#173 id=173 data-nosnippet>173</a> /// always get a string and can check emptiness. Mirrors Go's map[string]string
<a href=#174 id=174 data-nosnippet>174</a> /// zero-value semantics.
<a href=#175 id=175 data-nosnippet>175</a> </span><span class="attr">#[serde(default, deserialize_with = <span class="string">"deserialize_contents_map"</span>)]
<a href=#176 id=176 data-nosnippet>176</a> </span><span class="kw">pub </span>contents: BTreeMap<String, BTreeMap<String, String>>,
<a href=#177 id=177 data-nosnippet>177</a> <span class="doccomment">/// Pagination links.
<a href=#178 id=178 data-nosnippet>178</a> </span><span class="attr">#[serde(default)]
<a href=#179 id=179 data-nosnippet>179</a> </span><span class="kw">pub </span>links: CrawlerContentsLinks,
<a href=#180 id=180 data-nosnippet>180</a>}
<a href=#181 id=181 data-nosnippet>181</a>
<a href=#182 id=182 data-nosnippet>182</a><span class="doccomment">/// Deserialize `{url: {format: string|null}}` tolerating `null` inner values
<a href=#183 id=183 data-nosnippet>183</a>/// by mapping them to the empty string.
<a href=#184 id=184 data-nosnippet>184</a></span><span class="kw">fn </span>deserialize_contents_map<<span class="lifetime">'de</span>, D>(
<a href=#185 id=185 data-nosnippet>185</a> deserializer: D,
<a href=#186 id=186 data-nosnippet>186</a>) -> <span class="prelude-ty">Result</span><BTreeMap<String, BTreeMap<String, String>>, D::Error>
<a href=#187 id=187 data-nosnippet>187</a><span class="kw">where
<a href=#188 id=188 data-nosnippet>188</a> </span>D: serde::Deserializer<<span class="lifetime">'de</span>>,
<a href=#189 id=189 data-nosnippet>189</a>{
<a href=#190 id=190 data-nosnippet>190</a> <span class="kw">let </span>raw: BTreeMap<String, BTreeMap<String, <span class="prelude-ty">Option</span><String>>> =
<a href=#191 id=191 data-nosnippet>191</a> BTreeMap::deserialize(deserializer)<span class="question-mark">?</span>;
<a href=#192 id=192 data-nosnippet>192</a> <span class="prelude-val">Ok</span>(raw
<a href=#193 id=193 data-nosnippet>193</a> .into_iter()
<a href=#194 id=194 data-nosnippet>194</a> .map(|(url, by_format)| {
<a href=#195 id=195 data-nosnippet>195</a> (
<a href=#196 id=196 data-nosnippet>196</a> url,
<a href=#197 id=197 data-nosnippet>197</a> by_format
<a href=#198 id=198 data-nosnippet>198</a> .into_iter()
<a href=#199 id=199 data-nosnippet>199</a> .map(|(fmt, body)| (fmt, body.unwrap_or_default()))
<a href=#200 id=200 data-nosnippet>200</a> .collect(),
<a href=#201 id=201 data-nosnippet>201</a> )
<a href=#202 id=202 data-nosnippet>202</a> })
<a href=#203 id=203 data-nosnippet>203</a> .collect())
<a href=#204 id=204 data-nosnippet>204</a>}
<a href=#205 id=205 data-nosnippet>205</a>
<a href=#206 id=206 data-nosnippet>206</a><span class="doccomment">/// Pagination links returned with bulk contents.
<a href=#207 id=207 data-nosnippet>207</a>///
<a href=#208 id=208 data-nosnippet>208</a>/// `next`/`prev` arrive as JSON `null` when there is no adjacent page, which
<a href=#209 id=209 data-nosnippet>209</a>/// would reject under a plain `String` field; [`null_as_empty_string`] maps
<a href=#210 id=210 data-nosnippet>210</a>/// both null and absent to the empty string so the public API stays typed.
<a href=#211 id=211 data-nosnippet>211</a></span><span class="attr">#[derive(Debug, Clone, Deserialize, Default)]
<a href=#212 id=212 data-nosnippet>212</a></span><span class="kw">pub struct </span>CrawlerContentsLinks {
<a href=#213 id=213 data-nosnippet>213</a> <span class="doccomment">/// Crawled URLs link.
<a href=#214 id=214 data-nosnippet>214</a> </span><span class="attr">#[serde(default, deserialize_with = <span class="string">"null_as_empty_string"</span>)]
<a href=#215 id=215 data-nosnippet>215</a> </span><span class="kw">pub </span>crawled_urls: String,
<a href=#216 id=216 data-nosnippet>216</a> <span class="doccomment">/// Next-page link (empty when on the last page).
<a href=#217 id=217 data-nosnippet>217</a> </span><span class="attr">#[serde(default, deserialize_with = <span class="string">"null_as_empty_string"</span>)]
<a href=#218 id=218 data-nosnippet>218</a> </span><span class="kw">pub </span>next: String,
<a href=#219 id=219 data-nosnippet>219</a> <span class="doccomment">/// Previous-page link (empty when on the first page).
<a href=#220 id=220 data-nosnippet>220</a> </span><span class="attr">#[serde(default, deserialize_with = <span class="string">"null_as_empty_string"</span>)]
<a href=#221 id=221 data-nosnippet>221</a> </span><span class="kw">pub </span>prev: String,
<a href=#222 id=222 data-nosnippet>222</a>}
<a href=#223 id=223 data-nosnippet>223</a>
<a href=#224 id=224 data-nosnippet>224</a><span class="doccomment">/// Coerce JSON `null | absent | string` into a plain `String`, where null
<a href=#225 id=225 data-nosnippet>225</a>/// and absent both collapse to the empty string. Mirrors Go's `string`
<a href=#226 id=226 data-nosnippet>226</a>/// zero-value behavior under `encoding/json`.
<a href=#227 id=227 data-nosnippet>227</a></span><span class="kw">fn </span>null_as_empty_string<<span class="lifetime">'de</span>, D>(deserializer: D) -> <span class="prelude-ty">Result</span><String, D::Error>
<a href=#228 id=228 data-nosnippet>228</a><span class="kw">where
<a href=#229 id=229 data-nosnippet>229</a> </span>D: serde::Deserializer<<span class="lifetime">'de</span>>,
<a href=#230 id=230 data-nosnippet>230</a>{
<a href=#231 id=231 data-nosnippet>231</a> <span class="prelude-val">Ok</span>(Option::<String>::deserialize(deserializer)<span class="question-mark">?</span>.unwrap_or_default())
<a href=#232 id=232 data-nosnippet>232</a>}
<a href=#233 id=233 data-nosnippet>233</a>
<a href=#234 id=234 data-nosnippet>234</a><span class="doccomment">/// Typed content wrapper for a single crawled URL (`Crawl::read`).
<a href=#235 id=235 data-nosnippet>235</a></span><span class="attr">#[derive(Debug, Clone, Default)]
<a href=#236 id=236 data-nosnippet>236</a></span><span class="kw">pub struct </span>CrawlContent {
<a href=#237 id=237 data-nosnippet>237</a> <span class="doccomment">/// URL.
<a href=#238 id=238 data-nosnippet>238</a> </span><span class="kw">pub </span>url: String,
<a href=#239 id=239 data-nosnippet>239</a> <span class="doccomment">/// Content in the requested format.
<a href=#240 id=240 data-nosnippet>240</a> </span><span class="kw">pub </span>content: String,
<a href=#241 id=241 data-nosnippet>241</a> <span class="doccomment">/// Parent crawler UUID.
<a href=#242 id=242 data-nosnippet>242</a> </span><span class="kw">pub </span>crawl_uuid: String,
<a href=#243 id=243 data-nosnippet>243</a>}
<a href=#244 id=244 data-nosnippet>244</a>
<a href=#245 id=245 data-nosnippet>245</a><span class="doccomment">/// Artifact type — `warc` or `har`.
<a href=#246 id=246 data-nosnippet>246</a></span><span class="attr">#[derive(Debug, Clone, Copy, PartialEq, Eq)]
<a href=#247 id=247 data-nosnippet>247</a></span><span class="kw">pub enum </span>CrawlerArtifactType {
<a href=#248 id=248 data-nosnippet>248</a> <span class="doccomment">/// WARC artifact.
<a href=#249 id=249 data-nosnippet>249</a> </span>Warc,
<a href=#250 id=250 data-nosnippet>250</a> <span class="doccomment">/// HAR artifact.
<a href=#251 id=251 data-nosnippet>251</a> </span>Har,
<a href=#252 id=252 data-nosnippet>252</a>}
<a href=#253 id=253 data-nosnippet>253</a>
<a href=#254 id=254 data-nosnippet>254</a><span class="kw">impl </span>CrawlerArtifactType {
<a href=#255 id=255 data-nosnippet>255</a> <span class="doccomment">/// Wire-format string.
<a href=#256 id=256 data-nosnippet>256</a> </span><span class="kw">pub fn </span>as_str(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span><span class="lifetime">'static </span>str {
<a href=#257 id=257 data-nosnippet>257</a> <span class="kw">match </span><span class="self">self </span>{
<a href=#258 id=258 data-nosnippet>258</a> <span class="self">Self</span>::Warc => <span class="string">"warc"</span>,
<a href=#259 id=259 data-nosnippet>259</a> <span class="self">Self</span>::Har => <span class="string">"har"</span>,
<a href=#260 id=260 data-nosnippet>260</a> }
<a href=#261 id=261 data-nosnippet>261</a> }
<a href=#262 id=262 data-nosnippet>262</a>}
<a href=#263 id=263 data-nosnippet>263</a>
<a href=#264 id=264 data-nosnippet>264</a><span class="doccomment">/// WARC or HAR artifact downloaded from the crawler endpoint.
<a href=#265 id=265 data-nosnippet>265</a></span><span class="attr">#[derive(Debug, Clone)]
<a href=#266 id=266 data-nosnippet>266</a></span><span class="kw">pub struct </span>CrawlerArtifact {
<a href=#267 id=267 data-nosnippet>267</a> <span class="doccomment">/// Artifact type.
<a href=#268 id=268 data-nosnippet>268</a> </span><span class="kw">pub </span>artifact_type: CrawlerArtifactType,
<a href=#269 id=269 data-nosnippet>269</a> <span class="doccomment">/// Raw bytes.
<a href=#270 id=270 data-nosnippet>270</a> </span><span class="kw">pub </span>data: Bytes,
<a href=#271 id=271 data-nosnippet>271</a>}
<a href=#272 id=272 data-nosnippet>272</a>
<a href=#273 id=273 data-nosnippet>273</a><span class="kw">impl </span>CrawlerArtifact {
<a href=#274 id=274 data-nosnippet>274</a> <span class="doccomment">/// Write the artifact to disk.
<a href=#275 id=275 data-nosnippet>275</a> </span><span class="kw">pub fn </span>save(<span class="kw-2">&</span><span class="self">self</span>, path: <span class="kw-2">&</span>std::path::Path) -> std::io::Result<()> {
<a href=#276 id=276 data-nosnippet>276</a> std::fs::write(path, <span class="kw-2">&</span><span class="self">self</span>.data)
<a href=#277 id=277 data-nosnippet>277</a> }
<a href=#278 id=278 data-nosnippet>278</a> <span class="doccomment">/// Byte length of the artifact.
<a href=#279 id=279 data-nosnippet>279</a> </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize {
<a href=#280 id=280 data-nosnippet>280</a> <span class="self">self</span>.data.len()
<a href=#281 id=281 data-nosnippet>281</a> }
<a href=#282 id=282 data-nosnippet>282</a> <span class="doccomment">/// True when empty.
<a href=#283 id=283 data-nosnippet>283</a> </span><span class="kw">pub fn </span>is_empty(<span class="kw-2">&</span><span class="self">self</span>) -> bool {
<a href=#284 id=284 data-nosnippet>284</a> <span class="self">self</span>.data.is_empty()
<a href=#285 id=285 data-nosnippet>285</a> }
<a href=#286 id=286 data-nosnippet>286</a>}
</code></pre></div></section></main></body></html>