reqwest-scraper 0.6.2

Web scraping integration with reqwest
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

#![deny(missing_docs)]

//! reqwest-scraper
//#![doc = include_str!("../README.md")]

#[cfg(feature = "css_selector")]
pub mod css_selector;
pub mod error;
#[cfg(feature = "jsonpath")]
pub mod jsonpath;
#[cfg(feature = "xpath")]
pub mod xpath;

#[cfg(feature = "css_selector")]
use crate::css_selector::Html;
use crate::error::Result;
#[cfg(feature = "jsonpath")]
use crate::jsonpath::Json;
#[cfg(feature = "xpath")]
use crate::xpath::XHtml;
use async_trait::async_trait;
use encoding_rs::{Encoding, UTF_8};
use error::ScraperError;
use mime::Mime;
pub use reqwest::Response;

pub use reqwest_scraper_macros::{FromCssSelector, FromXPath, include_http};

/// Use XPath to extract the HTML response body into the derived struct
#[cfg(feature = "xpath")]
pub trait FromXPath {
    /// extract result by xpath
    type XPathExtractResult;

    /// From Html Response
    fn from_xhtml(html: XHtml) -> Self::XPathExtractResult;
}

/// Use CssSelector to extract the HTML response body into the derived struct
#[cfg(feature = "css_selector")]
pub trait FromCssSelector {
    /// extract result by css selector
    type CssSelectorExtractResult;

    /// From Html Response
    fn from_html(html: Html) -> Self::CssSelectorExtractResult;
}

/// Support extended traits of jsonpath, css selector, and xpath
#[async_trait]
pub trait ScraperResponse {
    /// Use jsonpath to select the response body
    #[cfg(feature = "jsonpath")]
    async fn jsonpath(self) -> Result<Json>;

    /// Use CSS selector to select the response body
    #[cfg(feature = "css_selector")]
    async fn css_selector(self) -> Result<Html>;

    /// Use XPath to select the response body
    #[cfg(feature = "xpath")]
    async fn xpath(self) -> Result<XHtml>;

    /// If there is no Encoding method in the Content-Type of the response header,
    /// try to read the meta information in the HTML to obtain the encoding.
    /// eg: <meta charset="gb2312">
    async fn html(self) -> Result<String>;
}

#[async_trait]
impl ScraperResponse for Response {
    #[cfg(feature = "jsonpath")]
    async fn jsonpath(self) -> Result<Json> {
        if self.status().is_success() {
            let json = self.text().await?;
            Ok(Json::new(json.as_str())?)
        } else {
            let url = self.url().to_string();
            let status_code = self.status().as_u16();
            let response = self.text().await?;
            Err(ScraperError::HttpError(url, status_code, response))
        }
    }

    #[cfg(feature = "css_selector")]
    async fn css_selector(self) -> Result<Html> {
        if self.status().is_success() {
            let html_str = self.html().await?;
            Ok(Html::new(html_str.as_str()))
        } else {
            let url = self.url().to_string();
            let status_code = self.status().as_u16();
            let response = self.text().await?;
            Err(ScraperError::HttpError(url, status_code, response))
        }
    }

    #[cfg(feature = "xpath")]
    async fn xpath(self) -> Result<XHtml> {
        if self.status().is_success() {
            let html_str = self.html().await?;
            Ok(XHtml::new(html_str)?)
        } else {
            let url = self.url().to_string();
            let status_code = self.status().as_u16();
            let response = self.text().await?;
            Err(ScraperError::HttpError(url, status_code, response))
        }
    }

    async fn html(self) -> Result<String> {
        let content_type = self
            .headers()
            .get(reqwest::header::CONTENT_TYPE)
            .and_then(|value| value.to_str().ok())
            .and_then(|value| value.parse::<Mime>().ok());
        let encoding_name = content_type
            .as_ref()
            .and_then(|mime| mime.get_param("charset").map(|charset| charset.as_str()));

        let full = self.bytes().await?;
        match encoding_name {
            Some(encoding_name) => {
                let encoding = Encoding::for_label(encoding_name.as_bytes()).unwrap_or(UTF_8);
                let (text, _, _) = encoding.decode(&full);
                Ok(text.into_owned())
            }
            None => {
                let (text, _, _) = UTF_8.decode(&full);
                let meta_charset = extract_charset(&text);
                if let Some(meta_charset) = meta_charset {
                    let encoding = Encoding::for_label(meta_charset.as_bytes()).unwrap_or(UTF_8);
                    let (text, _, _) = encoding.decode(&full);
                    Ok(text.into_owned())
                } else {
                    Ok(text.into_owned())
                }
            }
        }
    }
}

fn extract_charset(html: &str) -> Option<String> {
    let meta_start = "<meta charset=";
    if let Some(start_index) = html.find(meta_start) {
        let start = start_index + meta_start.len();

        // 查找第一个引号，确定是单引号还是双引号
        let quote_char = html[start..].chars().next()?;

        // 如果不是引号字符，返回None
        if quote_char != '"' && quote_char != '\'' {
            return None;
        }

        // 查找下一个引号，确定编码值的结束位置
        let end_quote = html[start + 1..].find(quote_char)? + start + 1;

        // 提取编码值
        let charset = &html[start + 1..end_quote];
        return Some(charset.to_string());
    }

    None
}

mod tests {

    #[test]
    fn test_extract_charset() {
        use super::extract_charset;
        let html = r#"
        <!DOCTYPE html>
        <html>
        <head>
            <meta charset="gb2312">
            <title>Example</title>
        </head>
        <body><p>Hello, world!</p></body>
        </html>
        "#;

        let cs = extract_charset(html);
        assert!(cs.is_some());
        assert_eq!(cs.unwrap(), "gb2312");

        let html = r#"
        <!DOCTYPE html>
        <html>
        <head>
            <meta charset='gb2312'>
            <title>Example</title>
        </head>
        <body><p>Hello, world!</p></body>
        </html>
        "#;

        let cs = extract_charset(html);
        assert!(cs.is_some());
        assert_eq!(cs.unwrap(), "gb2312");
    }
}