利用PHP爬虫按关键字搜索1688商品：实战指南

1. 准备工作

在开始之前，请确保：

• 你有基本的PHP编程知识
• 服务器已安装PHP（建议7.0+版本）
• 了解HTTP请求和HTML解析基础

2. 分析1688搜索接口

1688的搜索页面是：https://s.1688.com/selloffer/offer_search.htm

通过浏览器开发者工具分析，我们可以发现：

• 搜索请求是POST/GET方式
• 需要传递的关键参数包括：keywords（搜索词）、beginPage（页码）等

3. 基本PHP爬虫实现

方法一：使用file_get_contents和正则表达式

php

	<?php
	function search1688($keywords, $page = 1) {
	$url = "https://s.1688.com/selloffer/offer_search.htm?keywords=" . urlencode($keywords) . "&beginPage=" . $page;
	// 设置用户代理模拟浏览器访问
	$options = [
	'http' => [
	'method' => 'GET',
	'header' => "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36\r\n"
	]
	];
	$context = stream_context_create($options);
	// 获取页面内容
	$html = file_get_contents($url, false, $context);
	if ($html === false) {
	return ['error' => '无法获取页面内容'];
	}
	// 使用正则表达式提取商品信息
	preg_match_all('/<div class="item">.*?<a href="(.*?)" title="(.*?)">.*?<span class="price">([^<]+)</span>.*?</div>/s', $html, $matches, PREG_SET_ORDER);
	$results = [];
	foreach ($matches as $match) {
	$results[] = [
	'url' => $match[1],
	'title' => $match[2],
	'price' => $match[3]
	];
	}
	return $results;
	}
	// 使用示例
	$products = search1688('手机壳');
	print_r($products);
	?>

方法二：使用cURL和DOM解析（推荐）

php

	<?php
	function search1688WithCurl($keywords, $page = 1) {
	$url = "https://s.1688.com/selloffer/offer_search.htm?keywords=" . urlencode($keywords) . "&beginPage=" . $page;
	$ch = curl_init();
	curl_setopt($ch, CURLOPT_URL, $url);
	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
	curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
	curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36');
	$html = curl_exec($ch);
	curl_close($ch);
	if (!$html) {
	return ['error' => '无法获取页面内容'];
	}
	// 使用DOMDocument解析HTML
	$dom = new DOMDocument();
	@$dom->loadHTML($html);
	$xpath = new DOMXPath($dom);
	// 查找商品元素
	$items = $xpath->query("//div[contains(@class, 'item')]");
	$results = [];
	foreach ($items as $item) {
	$titleElement = $xpath->query(".//a[contains(@class, 'title')]", $item)->item(0);
	$priceElement = $xpath->query(".//span[contains(@class, 'price')]", $item)->item(0);
	$product = [
	'title' => $titleElement ? trim($titleElement->nodeValue) : '',
	'price' => $priceElement ? trim($priceElement->nodeValue) : '',
	'url' => $titleElement ? $titleElement->getAttribute('href') : ''
	];
	$results[] = $product;
	}
	return $results;
	}
	// 使用示例
	$products = search1688WithCurl('手机壳');
	print_r($products);
	?>

4. 处理反爬机制

1688有反爬机制，可能需要处理：

4.1 设置合理的请求头

php

	$headers = [
	'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
	'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
	'Accept-Language: zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
	'Referer: https://www.1688.com/',
	'DNT: 1'
	];
	curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

4.2 使用代理IP

php

	curl_setopt($ch, CURLOPT_PROXY, 'proxy_ip:port');
	curl_setopt($ch, CURLOPT_PROXYUSERPWD, 'username:password'); // 如果需要认证

4.3 限制请求频率

php

	// 在多次请求之间添加延迟
	sleep(rand(1, 3));

5. 使用API接口（推荐）

如果频繁爬取，建议使用1688官方API（需要申请权限）：

php

	function search1688ViaAPI($keywords, $page = 1) {
	$appKey = '你的APP_KEY';
	$appSecret = '你的APP_SECRET';
	$params = [
	'method' => 'alibaba.offer.search',
	'app_key' => $appKey,
	'timestamp' => date('Y-m-d H:i:s'),
	'format' => 'json',
	'v' => '2.0',
	'keywords' => $keywords,
	'page_no' => $page
	];
	// 生成签名
	ksort($params);
	$stringToSign = $appSecret;
	foreach ($params as $k => $v) {
	$stringToSign .= "$k$v";
	}
	$stringToSign .= $appSecret;
	$params['sign'] = strtoupper(md5($stringToSign));
	$queryString = http_build_query($params);
	$url = 'http://gw.api.1688.com/openapi?' . $queryString;
	$response = file_get_contents($url);
	return json_decode($response, true);
	}

6. 完整示例代码

php

	<?php
	class Ali1688Crawler {
	private $userAgent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36';
	private $delay = 2; // 请求间隔时间(秒)
	public function search($keywords, $page = 1, $useApi = false) {
	if ($useApi) {
	return $this->searchViaAPI($keywords, $page);
	} else {
	return $this->searchViaCrawler($keywords, $page);
	}
	}
	private function searchViaCrawler($keywords, $page) {
	$url = "https://s.1688.com/selloffer/offer_search.htm?keywords=" . urlencode($keywords) . "&beginPage=" . $page;
	$ch = curl_init();
	curl_setopt($ch, CURLOPT_URL, $url);
	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
	curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
	curl_setopt($ch, CURLOPT_USERAGENT, $this->userAgent);
	curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
	$html = curl_exec($ch);
	curl_close($ch);
	if (!$html) {
	return ['error' => '无法获取页面内容'];
	}
	$dom = new DOMDocument();
	@$dom->loadHTML(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'));
	$xpath = new DOMXPath($dom);
	$items = $xpath->query("//div[contains(@class, 'item')]");
	$results = [];
	foreach ($items as $item) {
	try {
	$titleElement = $xpath->query(".//a[contains(@class, 'title')]", $item)->item(0);
	$priceElement = $xpath->query(".//span[contains(@class, 'price')]", $item)->item(0);
	$salesElement = $xpath->query(".//span[contains(@class, 'sale-num')]", $item)->item(0);
	$product = [
	'title' => $titleElement ? trim($titleElement->nodeValue) : '',
	'price' => $priceElement ? trim($priceElement->nodeValue) : '',
	'sales' => $salesElement ? preg_replace('/[^0-9]/', '', $salesElement->nodeValue) : 0,
	'url' => $titleElement ? $this->getAbsoluteUrl($titleElement->getAttribute('href')) : ''
	];
	$results[] = $product;
	} catch (Exception $e) {
	continue;
	}
	}
	// 添加延迟以避免被封
	sleep($this->delay);
	return $results;
	}
	private function getAbsoluteUrl($relativeUrl) {
	if (strpos($relativeUrl, 'http') === 0) {
	return $relativeUrl;
	}
	return 'https:' . $relativeUrl;
	}
	private function searchViaAPI($keywords, $page) {
	// 这里需要替换为你的实际API密钥
	$appKey = 'your_app_key';
	$appSecret = 'your_app_secret';
	$params = [
	'method' => 'alibaba.offer.search',
	'app_key' => $appKey,
	'timestamp' => date('Y-m-d H:i:s'),
	'format' => 'json',
	'v' => '2.0',
	'keywords' => $keywords,
	'page_no' => $page,
	'fields' => 'title,price,sale_num,detail_url'
	];
	// 生成签名
	ksort($params);
	$stringToSign = $appSecret;
	foreach ($params as $k => $v) {
	$stringToSign .= "$k$v";
	}
	$stringToSign .= $appSecret;
	$params['sign'] = strtoupper(md5($stringToSign));
	$queryString = http_build_query($params);
	$url = 'http://gw.api.1688.com/openapi?' . $queryString;
	$response = file_get_contents($url);
	$result = json_decode($response, true);
	if (isset($result['error_response'])) {
	return ['error' => $result['error_response']['sub_msg'] ?? 'API请求失败'];
	}
	$products = [];
	if (isset($result['response']['offers']['offer'])) {
	foreach ($result['response']['offers']['offer'] as $offer) {
	$products[] = [
	'title' => $offer['title'] ?? '',
	'price' => $offer['price'] ?? '',
	'sales' => $offer['sale_num'] ?? 0,
	'url' => $offer['detail_url'] ?? ''
	];
	}
	}
	return $products;
	}
	}
	// 使用示例
	$crawler = new Ali1688Crawler();
	// 使用爬虫方式
	$products = $crawler->search('手机壳', 1, false);
	print_r($products);
	// 使用API方式（需要申请权限）
	// $apiProducts = $crawler->search('手机壳', 1, true);
	// print_r($apiProducts);
	?>

7. 注意事项

1. 法律合规性：爬取1688数据前请确保遵守1688的robots.txt和服务条款，避免法律风险
2. 请求频率：控制请求频率，避免被封IP
3. 反爬机制：1688可能会更新反爬策略，需要持续关注和调整
4. API优先：如果可能，优先使用官方API接口
5. 数据解析：1688页面结构可能变化，需要定期检查并更新解析逻辑

8. 替代方案

如果遇到爬取困难，可以考虑：

• 使用Selenium等浏览器自动化工具模拟真实用户行为
• 使用现成的爬虫框架如Goutte、Panther等
• 购买商业数据服务

希望这个指南对你有所帮助！记得在实际应用中遵守相关法律法规和网站的使用条款。