hak8or/greasemonkey_scripts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Moved ebay scraping into separate directory and added rust version

Browse Source
This commit is contained in:
hak8or
2025-05-29 00:29:53 -04:00
parent 89bd668a9c
commit c1af98d1c2
12 changed files with 2806 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

547
ebay_storage/rust/src/main.rs Normal file
View File

@ -0,0 +1,547 @@
// main.rs
// Import necessary crates
use clap::Parser;
use regex::Regex;
use scraper::{Html, Selector};
use serde::Serialize;
use std::fs::{self, File};
use std::io::Write;
use std::path::{Path, PathBuf};
use std::error::Error;
use chrono::{DateTime, Utc};
use lazy_static::lazy_static;
use url::Url;
// Define constants
const PARSER_ENGINE_VERSION: i32 = 1;
const USER_AGENT: &str = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36";
// --- Lazy static Regex definitions ---
lazy_static! {
// Regex for parsing quantity from title (e.g., "LOT OF 10", "5-PACK")
static ref EXPLICIT_QTY_PATTERNS: Vec<Regex> = vec![
Regex::new(r"\b(?:LOT\s+OF|LOT)\s*\(?\s*(\d+)\s*\)?").unwrap(),
Regex::new(r"\b(?:LOT\s+OF|LOT)\s*\*\s*(\d+)").unwrap(),
Regex::new(r"\b(?:PACK\s+OF|PACK|BULK)\s*\(?\s*(\d+)\s*\)?").unwrap(),
Regex::new(r"\b(\d+)\s*-\s*PACK\b").unwrap(),
Regex::new(r"\b(\d+)\s*COUNT\b").unwrap(),
];
// Regex for parsing size from title (e.g., "500GB", "2TB")
static ref SIZE_REGEX: Regex = Regex::new(r"(\d+(?:\.\d+)?)\s*(TB|GB)\b").unwrap();
// Regex for titles indicating a range of sizes or mixed items
static ref SIZE_RANGE_REGEX: Regex = Regex::new(r"\d+(?:\.\d+)?\s*(?:GB|TB)\s*(?:-|&|OR|TO)\s*\d+(?:\.\d+)?\s*(?:GB|TB)").unwrap();
// Regex for extracting item ID from URL
static ref ITEM_ID_REGEX: Regex = Regex::new(r"/itm/(\d+)").unwrap();
// Regex for parsing price, potentially a range
static ref PRICE_REGEX: Regex = Regex::new(r"\$?([\d,]+\.?\d*)").unwrap();
// Regex for "NEW LISTING" prefix - case-insensitive to better match JS /i flag
static ref NEW_LISTING_REGEX: Regex = Regex::new(r"(?i)^\s*NEW LISTING\s*[:\-\s]*").unwrap();
}
// --- Command Line Argument Parsing (using clap) ---
#[derive(Parser, Debug)]
#[clap(name = "ebay-scraper-rust", version = "0.1.0", about = "Scrapes eBay search results for SSD/HDD cost per TB.")]
struct Cli {
#[clap(subcommand)]
command: Option<Commands>,
/// The full eBay search URL to scrape.
url: Option<String>,
/// Save scraped HTML to a file (and download images if fetching from URL).
#[clap(long)]
save: Option<String>,
/// Load HTML from a file (disables network). Image download will not occur with --load.
#[clap(long)]
load: Option<String>,
/// Suppress informational logs, output only final JSON.
#[clap(long)]
only_json: bool,
}
#[derive(Parser, Debug)]
enum Commands {
/// Scrapes latest listings.
Latest(LatestArgs),
}
#[derive(Parser, Debug)]
struct LatestArgs {
/// Items per page (60, 120, or 240)
#[clap(long, default_value = "60")]
per_page: String, // Keep as string for validation
/// Minimum cost (e.g., 50.00)
#[clap(long, default_value = "0.00")]
minimum_cost: f64,
}
// --- Data Structures for Scraped Items (using serde) ---
#[derive(Serialize, Debug)]
struct EbayItem {
title: String,
#[serde(rename = "itemId")]
item_id: String,
#[serde(rename = "dateFound")]
date_found: DateTime<Utc>,
#[serde(rename = "currentBidPrice")]
current_bid_price: Option<f64>,
#[serde(rename = "buyItNowPrice", skip_serializing_if = "Option::is_none")] // Keep skip for this one if JS does it
buy_it_now_price: Option<f64>,
#[serde(rename = "hasBestOffer")]
has_best_offer: bool,
#[serde(skip_serializing_if = "Option::is_none")] // Keep skip for this one if JS does it
image_url: Option<String>,
parsed: ParsedItemData,
}
#[derive(Serialize, Debug)]
struct ParsedItemData {
#[serde(rename = "itemCount")]
item_count: i32,
// MODIFIED: Removed skip_serializing_if to always include the field, even if null
#[serde(rename = "sizePerItemTB")]
size_per_item_tb: Option<f64>,
#[serde(rename = "totalTB")]
total_tb: Option<f64>,
#[serde(rename = "costPerTB")]
cost_per_tb: Option<f64>,
#[serde(rename = "needed_description_check")]
needed_description_check: bool,
#[serde(rename = "parser_engine")]
parser_engine: i32,
}
#[derive(Debug)]
struct SizeQuantityInfo {
total_tb: f64,
quantity: i32,
individual_size_tb: f64,
needed_description_check: bool,
}
// --- Logging ---
fn log_message(message: &str, quiet_mode: bool) {
if !quiet_mode {
eprintln!("{}", message);
}
}
fn log_error(message: &str, quiet_mode: bool) {
if !quiet_mode {
eprintln!("ERROR: {}", message);
}
}
// --- Parsing Logic ---
mod parser {
use super::*;
/// Parses size and quantity information from an item title.
pub fn parse_size_and_quantity(title: &str) -> SizeQuantityInfo {
let upper_title = title.to_uppercase();
let mut total_tb = 0.0;
let mut quantity = 1;
let mut needed_description_check = false;
let mut individual_size_tb = 0.0;
for pattern in EXPLICIT_QTY_PATTERNS.iter() {
if let Some(caps) = pattern.captures(&upper_title) {
if let Some(qty_match) = caps.get(1) {
if let Ok(parsed_qty) = qty_match.as_str().parse::<i32>() {
if parsed_qty > 0 && parsed_qty < 500 {
quantity = parsed_qty;
break;
}
}
}
}
}
let mut size_matches: Vec<(f64, String)> = Vec::new();
for caps in SIZE_REGEX.captures_iter(&upper_title) {
if let (Some(val_str), Some(unit_str)) = (caps.get(1), caps.get(2)) {
if let Ok(val) = val_str.as_str().parse::<f64>() {
size_matches.push((val, unit_str.as_str().to_string()));
}
}
}
if !size_matches.is_empty() {
let mut unique_sizes_tb: Vec<f64> = size_matches.iter()
.map(|(val, unit)| if unit == "GB" { *val / 1000.0 } else { *val })
.collect();
unique_sizes_tb.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal));
unique_sizes_tb.dedup();
if !unique_sizes_tb.is_empty() {
individual_size_tb = unique_sizes_tb[0];
if unique_sizes_tb.len() > 1 {
needed_description_check = true;
}
}
}
if SIZE_RANGE_REGEX.is_match(&upper_title) {
needed_description_check = true;
}
if quantity > 1 && upper_title.contains("MIXED") {
needed_description_check = true;
}
if upper_title.contains("CHECK THE DESCRIPTION") || upper_title.contains("CHECK DESCRIPTION") || upper_title.contains("SEE DESCRIPTION") {
if quantity > 1 || size_matches.is_empty() || size_matches.len() > 1 {
needed_description_check = true;
}
}
if individual_size_tb > 0.0 {
total_tb = individual_size_tb * quantity as f64;
}
if quantity > 1 && total_tb == 0.0 && !size_matches.is_empty() {
needed_description_check = true;
}
if quantity == 1 && size_matches.len() == 1 && !needed_description_check {
// This condition is implicitly handled
}
SizeQuantityInfo {
total_tb: (total_tb * 10000.0).round() / 10000.0,
quantity,
individual_size_tb: (individual_size_tb * 10000.0).round() / 10000.0,
needed_description_check,
}
}
/// Parses price from a string, taking the first price if it's a range.
pub fn parse_price(price_text: &str) -> Option<f64> {
let lower_price_text = price_text.to_lowercase();
if lower_price_text.contains(" to ") {
if let Some(first_part) = lower_price_text.split(" to ").next() {
if let Some(caps) = PRICE_REGEX.captures(first_part) {
if let Some(price_match) = caps.get(1) {
return price_match.as_str().replace(',', "").parse().ok();
}
}
}
return None;
}
if let Some(caps) = PRICE_REGEX.captures(price_text) {
if let Some(price_match) = caps.get(1) {
return price_match.as_str().replace(',', "").parse().ok();
}
}
None
}
}
// --- HTML Scraping Logic ---
mod html_scraper {
use super::*;
/// Extracts item data from HTML content.
pub fn extract_data_from_html(html_content: &str, quiet_mode: bool) -> Result<Vec<EbayItem>, Box<dyn Error>> {
let document = Html::parse_document(html_content);
let mut items = Vec::new();
let today = Utc::now();
let item_selector = Selector::parse("li.s-item, li.srp-results__item, div.s-item[role='listitem']").unwrap();
let title_selector = Selector::parse(".s-item__title, .srp-results__title").unwrap();
let price_selector = Selector::parse(".s-item__price").unwrap();
let image_selector = Selector::parse(".s-item__image-wrapper img.s-item__image-img, .s-item__image img").unwrap();
let link_selector = Selector::parse("a.s-item__link[href*='/itm/'], .s-item__info > a[href*='/itm/']").unwrap();
let bid_count_selector = Selector::parse(".s-item__bid-count").unwrap();
let best_offer_selector = Selector::parse(".s-item__purchase-options--bo, .s-item__best-offer").unwrap();
let secondary_info_selector = Selector::parse(".s-item__subtitle, .s-item__secondary-text, .s-item__detail--secondary").unwrap();
let auction_bin_price_selector = Selector::parse(".s-item__buy-it-now-price").unwrap();
for element in document.select(&item_selector) {
let raw_title_text = element.select(&title_selector).next().map(|el| el.text().collect::<String>().trim().to_string());
let price_text = element.select(&price_selector).next().map(|el| el.text().collect::<String>().trim().to_string());
let item_id = element.select(&link_selector).next()
.and_then(|link_el| link_el.value().attr("href"))
.and_then(|href| ITEM_ID_REGEX.captures(href))
.and_then(|caps| caps.get(1).map(|m| m.as_str().to_string()));
if raw_title_text.is_none() || price_text.is_none() || item_id.is_none() {
log_message("Skipping item due to missing title, price, or item ID.", quiet_mode);
continue;
}
let raw_title = raw_title_text.unwrap();
let price_text = price_text.unwrap();
let item_id = item_id.unwrap();
let cleaned_title = NEW_LISTING_REGEX.replace(&raw_title, "").trim().to_string();
let primary_display_price = parser::parse_price(&price_text);
let mut current_bid_price: Option<f64> = None;
let mut final_buy_it_now_price: Option<f64> = None;
let mut has_best_offer = false;
let mut item_is_auction = false;
if let Some(bid_el) = element.select(&bid_count_selector).next() {
if bid_el.text().collect::<String>().to_lowercase().contains("bid") {
item_is_auction = true;
}
}
if element.select(&best_offer_selector).next().is_some() {
has_best_offer = true;
} else {
for el in element.select(&secondary_info_selector) {
if el.text().collect::<String>().to_lowercase().contains("or best offer") {
has_best_offer = true;
break;
}
}
}
if item_is_auction {
current_bid_price = primary_display_price;
if let Some(bin_el) = element.select(&auction_bin_price_selector).next() {
final_buy_it_now_price = parser::parse_price(&bin_el.text().collect::<String>());
}
} else {
final_buy_it_now_price = primary_display_price;
}
let image_url_val = element.select(&image_selector).next()
.and_then(|img_el| {
img_el.value().attr("data-src").or(img_el.value().attr("src"))
})
.map(|s| s.to_string());
let parsed_size_info = parser::parse_size_and_quantity(&cleaned_title);
let cost_per_tb = if let Some(price) = primary_display_price {
if parsed_size_info.total_tb > 0.0 {
Some(((price / parsed_size_info.total_tb) * 100.0).round() / 100.0)
} else { None }
} else { None };
let parsed_data = ParsedItemData {
item_count: parsed_size_info.quantity,
size_per_item_tb: if parsed_size_info.individual_size_tb > 0.0 { Some(parsed_size_info.individual_size_tb) } else { None },
total_tb: if parsed_size_info.total_tb > 0.0 { Some(parsed_size_info.total_tb) } else { None },
cost_per_tb, // This will be None if conditions aren't met, and serialized as null
needed_description_check: parsed_size_info.needed_description_check,
parser_engine: PARSER_ENGINE_VERSION,
};
items.push(EbayItem {
title: cleaned_title,
item_id,
date_found: today,
current_bid_price,
buy_it_now_price: final_buy_it_now_price,
has_best_offer,
image_url: image_url_val,
parsed: parsed_data,
});
}
Ok(items)
}
/// Downloads an image from a URL and saves it, preserving path structure.
pub async fn download_image(image_url_str: &str, base_save_directory: &Path, quiet_mode: bool) -> Result<(), Box<dyn Error>> {
if image_url_str.is_empty() {
return Ok(());
}
let parsed_url = Url::parse(image_url_str)?;
let image_path_from_url = parsed_url.path().trim_start_matches('/');
if image_path_from_url.is_empty() {
return Err("Image URL has no path component".into());
}
let full_local_image_path = base_save_directory.join(image_path_from_url);
if let Some(parent_dir) = full_local_image_path.parent() {
fs::create_dir_all(parent_dir)?;
log_message(&format!("Ensured image directory exists: {}", parent_dir.display()), quiet_mode);
}
let client = reqwest::Client::builder().user_agent(USER_AGENT).build()?;
let response = client.get(image_url_str).send().await?;
if !response.status().is_success() {
return Err(format!("Failed to download image {}. Status: {}", image_url_str, response.status()).into());
}
let mut file = File::create(&full_local_image_path)?;
let content = response.bytes().await?;
file.write_all(&content)?;
log_message(&format!("Downloaded image: {}", full_local_image_path.display()), quiet_mode);
Ok(())
}
}
// --- Main Application Logic ---
#[tokio::main]
async fn main() -> Result<(), Box<dyn Error>> {
let cli = Cli::parse();
let quiet_mode = cli.only_json;
log_message("Starting scraping process...", quiet_mode);
let html_content_to_parse: String;
let mut should_download_images = false;
let mut image_base_save_dir: Option<PathBuf> = None;
if let Some(html_file) = &cli.load {
log_message(&format!("Loading HTML from {}...", html_file), quiet_mode);
html_content_to_parse = fs::read_to_string(html_file)?;
log_message("HTML loaded. Network requests for page content disabled.", quiet_mode);
} else {
let url_to_fetch = match (&cli.command, &cli.url) {
(Some(Commands::Latest(latest_args)), _) => {
let valid_per_page = ["60", "120", "240"];
if !valid_per_page.contains(&latest_args.per_page.as_str()) {
let err_msg = format!("--per_page must be one of {}, got {}", valid_per_page.join(", "), latest_args.per_page);
log_error(&err_msg, quiet_mode);
return Err(err_msg.into());
}
if latest_args.minimum_cost < 0.0 {
let err_msg = "--minimum_cost must be a non-negative number.";
log_error(err_msg, quiet_mode);
return Err(err_msg.into());
}
let base_url = "https://www.ebay.com/sch/i.html?_nkw=&_sacat=175669&_from=R40&_fsrp=1&LH_PrefLoc=3&imm=1&_sop=10";
let url = format!("{}&_ipg={}&_udlo={:.2}", base_url, latest_args.per_page, latest_args.minimum_cost);
log_message(&format!("Constructed URL for 'latest': {}", url), quiet_mode);
url
}
(None, Some(url_arg)) => {
url_arg.clone()
}
(None, None) => {
let err_msg = "No URL provided and no command specified. Use --help for usage.";
log_error(err_msg, true);
return Err(err_msg.into());
}
};
log_message(&format!("Navigating to {}...", url_to_fetch), quiet_mode);
let client = reqwest::Client::builder().user_agent(USER_AGENT).build()?;
let response = client.get(&url_to_fetch).send().await?;
if !response.status().is_success() {
let err_msg = format!("Failed to fetch URL: {} - Status: {}", url_to_fetch, response.status());
log_error(&err_msg, quiet_mode);
return Err(err_msg.into());
}
html_content_to_parse = response.text().await?;
log_message("Navigation successful. Page content retrieved.", quiet_mode);
if let Some(save_path_str) = &cli.save {
log_message(&format!("Saving HTML to {}...", save_path_str), quiet_mode);
let mut file = File::create(save_path_str)?;
file.write_all(html_content_to_parse.as_bytes())?;
log_message("HTML saved.", quiet_mode);
should_download_images = true;
let save_file_path = PathBuf::from(save_path_str);
let base_name = save_file_path.file_stem().unwrap_or_default().to_string_lossy().to_string();
if let Some(parent_dir) = save_file_path.parent() {
image_base_save_dir = Some(parent_dir.join(base_name));
} else {
image_base_save_dir = Some(PathBuf::from(base_name));
}
}
}
log_message("Extracting data...", quiet_mode);
let extracted_results = html_scraper::extract_data_from_html(&html_content_to_parse, quiet_mode)?;
log_message(&format!("Data extraction complete. Found {} items.", extracted_results.len()), quiet_mode);
if should_download_images && !extracted_results.is_empty() {
if let Some(img_base_dir) = image_base_save_dir {
log_message(&format!("Downloading images into subdirectories of {}...", img_base_dir.display()), quiet_mode);
let mut download_futures = Vec::new();
for item in &extracted_results {
if let Some(img_url) = &item.image_url {
let img_base_dir_clone = img_base_dir.clone();
let img_url_clone = img_url.clone();
let item_id_clone = item.item_id.clone();
download_futures.push(async move {
if let Err(e) = html_scraper::download_image(&img_url_clone, &img_base_dir_clone, quiet_mode).await {
log_error(&format!("Skipping image download for item ID {} (URL: {}) due to error: {}", item_id_clone, img_url_clone, e), quiet_mode);
}
});
}
}
futures::future::join_all(download_futures).await;
log_message("Image download process finished.", quiet_mode);
}
}
if quiet_mode {
println!("{}", serde_json::to_string(&extracted_results)?);
} else {
println!("{}", serde_json::to_string_pretty(&extracted_results)?);
}
Ok(())
}
// --- Unit tests for parser functions (optional, but good practice) ---
#[cfg(test)]
mod tests {
use super::parser::*;
use super::SizeQuantityInfo;
fn assert_sq_info_eq(actual: SizeQuantityInfo, expected_total_tb: f64, expected_quantity: i32, expected_ind_size_tb: f64, expected_check: bool) {
assert!((actual.total_tb - expected_total_tb).abs() < 0.0001, "TotalTB mismatch. Expected: {}, Got: {}", expected_total_tb, actual.total_tb);
assert_eq!(actual.quantity, expected_quantity, "Quantity mismatch");
assert!((actual.individual_size_tb - expected_ind_size_tb).abs() < 0.0001, "IndividualSizeTB mismatch. Expected: {}, Got: {}", expected_ind_size_tb, actual.individual_size_tb);
assert_eq!(actual.needed_description_check, expected_check, "NeededDescriptionCheck mismatch");
}
#[test]
fn test_parse_size_and_quantity() {
let test_cases = vec![
("LOT OF (9) MAJOR BRAND 2.5\" 7MM SSD * Kingston, Samsung, SanDisk& PNY*120-250GB", 1.080, 9, 0.120, true),
("Lot of 10 Intel 256 GB 2.5\" SATA SSD different Model check the Description", 2.560, 10, 0.256, true),
("Bulk 5 Lot Samsung 870 EVO 500GB SSD SATA - Used - Tested Passed Smart Test", 2.500, 5, 0.500, false),
("Samsung 1.6TB NVME PCIe 3.0 x8 2.75\" SSD MZPLK1T6HCHP PM1725 Series TLC", 1.6, 1, 1.6, false),
("Micron 5100 MAX 1.84TB SATA 6Gb/s 2.5\" SSD MTFDDAK1T9TCC-1AR1ZABYY", 1.84, 1, 1.84, false),
("10-PACK 1TB SSD", 10.0, 10, 1.0, false),
("2TB SSD NVMe", 2.0, 1, 2.0, false),
("WD Blue 500GB Internal SSD SATA III 6Gb/s", 0.5, 1, 0.5, false),
("Lot of 2 Mixed Capacity SSDs (120GB, 240GB) CHECK DESCRIPTION", 0.24, 2, 0.12, true),
("Single Drive 1TB", 1.0, 1, 1.0, false),
("Lot of 3 - CHECK DESCRIPTION - Mixed SSDs", 0.0, 3, 0.0, true),
];
for (title, total_tb, quantity, ind_size_tb, check) in test_cases {
println!("Testing title: {}", title);
let result = parse_size_and_quantity(title);
assert_sq_info_eq(result, total_tb, quantity, ind_size_tb, check);
}
}
#[test]
fn test_parse_price() {
assert_eq!(parse_price("$19.99"), Some(19.99));
assert_eq!(parse_price("USD 150.00"), Some(150.00));
assert_eq!(parse_price("$1,234.56"), Some(1234.56));
assert_eq!(parse_price("Free"), None);
assert_eq!(parse_price("$10.00 to $20.00"), Some(10.00));
assert_eq!(parse_price("EUR 25.50"), Some(25.50));
assert_eq!(parse_price("25.50"), Some(25.50));
}
}