DentalPlans.com Dentist Scraper 🦷

# Specify the base Docker image. You can read more about
# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-puppeteer-chrome

# Check preinstalled packages
RUN npm ls crawlee apify puppeteer playwright

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./


# Run the image.
CMD npm start --silent

{
    "actorSpecification": 1,
    "name": "dentalplans-com-dentist-scraper",
    "title": "Scrape single page in JavaScript",
    "description": "Scrape data from single page with provided URL.",
    "version": "0.0",
    "meta": {
        "templateId": "js-start"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
    "title": "DentalPlans.com Dentist Scraper Input",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "searchUrls": {
            "title": "Search URLs",
            "type": "array",
            "description": "List of DentalPlans.com search result URLs to scrape",
            "editor": "stringList",
            "default": ["https://www.dentalplans.com/dentist-search-results/?zip=90001&searchTerm="],
            "uniqueItems": true
        },
        "maxItems": {
            "title": "Maximum Items",
            "type": "integer",
            "description": "Maximum number of dentist records to scrape",
            "default": 100,
            "minimum": 1
        },
        "proxyConfiguration": {
            "title": "Proxy Configuration",
            "type": "object",
            "description": "Proxy settings for making requests",
            "default": {},
            "editor": "proxy"
        }
    },
    "required": ["searchUrls"]
}

1import { Actor } from 'apify';
2import { PuppeteerCrawler } from 'crawlee';
3import puppeteerExtra from 'puppeteer-extra';
4import randomUseragent from 'random-useragent';
5
6import rebrowserPuppeteer from 'rebrowser-puppeteer-core'
7
8puppeteerExtra.use(rebrowserPuppeteer)
9// puppeteerExtra.use(stealthPlugin());
10
11// const redisClient = new Redis("rediss://default:AY9xAAIjcDE2YTMyNjQyYTI5ODQ0NDQ3YjVhOTE1YWRiYWEyMTZjN3AxMA@sharing-wren-36721.upstash.io:6379");
12// let sessionid = await redisClient.get('instagram-sessionid-cookie');
13
14class DentalplansDentistScraper {
15    
16    async run(input) {
17        const { searchUrls, maxItems = Infinity, proxyConfiguration } = input;
18        this.maxItems = maxItems; // 存储maxItems为类属性
19
20        const proxyConfig = await Actor.createProxyConfiguration(proxyConfiguration);
21
22        for (const searchUrl of searchUrls) {
23            this.searchUrl = searchUrl;
24            let url = searchUrl;
25            const crawler = new PuppeteerCrawler({
26                proxyConfiguration: proxyConfig,
27                launchContext: {
28                    launcher: puppeteerExtra,
29                    launchOptions: {
30                        headless: true,
31                        args: [
32                            '--no-sandbox',
33                            '--disable-setuid-sandbox',
34                            '--disable-dev-shm-usage',
35                            '--disable-accelerated-2d-canvas',
36                            '--no-first-run',
37                            '--no-zygote',
38                            '--disable-gpu',
39                            '--disable-geolocation',
40                            '--disable-notifications',
41                            `--user-agent=${randomUseragent.getRandom(function (ua) {
42                                return ua.browserName === 'Chrome' && parseFloat(ua.browserVersion) >= 80;
43                            })}`,
44                        ],
45                    },
46                },
47                requestHandlerTimeoutSecs: 3600,    // 1小时超时
48                navigationTimeoutSecs: 300,         // 5分钟导航超时
49                preNavigationHooks: [
50                    async ({ page }) => {
51                        // 设置页面级别的超时时间
52                        await page.setDefaultNavigationTimeout(300000);  // 5分钟
53                        await page.setDefaultTimeout(300000);           // 5分钟
54                        // await this.setCookies(page);
55                    },
56                ],
57                requestHandler: async ({ page, request }) => {
58                    console.log(`Processing ${this.searchUrl}...`);
59                    let count = 0;
60                    let endOfResults = false;
61                    let interceptedData = []; // 初始化局部变量
62                    let lastDataLength = 0;
63                    let noNewDataCount = 0;
64                    const MAX_NO_NEW_DATA_COUNT = 5; // 10秒 / 2秒 = 5次
65
66                    await this.setupInterceptors(page, interceptedData);
67
68                    await page.goto(url);
69
70                    await this.randomDelay(2000, 3000);
71
72                    // while (!endOfResults && interceptedData.length < maxItems) {
73                    //     count++;
74                    //     console.log(`Scrolling time...${count}`);
75                    //     await this.randomDelay();
76                    //     await this.scrollPage(page);
77                    //     await this.randomDelay(2000, 3000);
78    
79
80                    //     endOfResults = await page.evaluate(() => {
81                    //         return document.body?.innerText?.includes('End of results');
82                    //     });
83
84                    //     if (endOfResults) {
85                    //         console.log('Reached end of results');
86                    //     } else if (interceptedData.length === lastDataLength) {
87                    //         noNewDataCount++;
88                    //         // console.log(`No new data for ${noNewDataCount * 5} seconds`);
89                    //         if (noNewDataCount >= MAX_NO_NEW_DATA_COUNT) {
90                    //             // console.log('No new data for 20 seconds, assuming end of results');
91                    //             endOfResults = true;
92                    //         }
93                    //     } else {
94                    //         noNewDataCount = 0;
95                    //         lastDataLength = interceptedData.length;
96                    //     }
97                    // }
98                },
99            });
100
101            await crawler.run([url]);
102        }
103    }
104
105    async setCookies(page) {
106        const cookies = [
107            {
108                name: '__Secure-ENID',
109                value: '25.SE=d-L9vS6M8r24MzgdqlRwPkwZ4XuLFnylPDuaGEeggzRxH7eCqUoC-FQmW_RkU9qFB1frSGan9ohnhJWzssbPggQub_gJCkNvv91vxYoy44oYgNXdZXTJuws_pKtdXhz7bPqxkLrLHVIXCBBiV1eY2ezXD0qJIByKpoFlCdMFqcQ6SUg6ZrMyrWE_omcoueLO-NOKhM0N1xG6yghXBVOZlZWwb8MkeNN1Ef5izW_yqbFxgrQgU4EDzHpjmPb-e93ySTJNBByYZVtugHaQyOJjG9NfaXftg97fOxEGw6WH3CTzgNX7dU2dsrim37epIaIg93Z5j4EcxImW_76hO1ulyFJySedL7yva2HtUUu8rxOS63rb_iifxWH2SO8MmSOlhg11rXon00umveuBjZNjhb_bHRYNqDwUl3wPlgZ7mhf5N9lGGwU9rRJ2bxgidWB1oxh82ut9BGplTQMy8mk_XzWCwlKhqDmNi9uOJCMn34uodH4fpCqYmhjYavGP7jtkOzmvAHaepAaO5RlGRseLeMq0k3_5E6p7bs8wnEc9yOcvi',
110                domain: '.google.com',
111                path: '/',
112                expires: new Date('2026-03-07T17:04:30.711Z').getTime() / 1000,
113                secure: true,
114                sameSite: 'Lax'
115            }
116            
117        ];
118
119        // 批量设置所有cookie
120        await Promise.all(cookies.map(cookie => page.setCookie(cookie)));
121    }
122
123    async setupInterceptors(page, interceptedData) {
124        await page.setRequestInterception(true);
125        page.on('request', (request) => {
126            // 获取资源类型
127            const resourceType = request.resourceType();
128            
129            // 需要过滤的资源类型
130            const blockedResourceTypes = [
131                // 'image',
132                // 'media', 
133                // 'font',
134                // 'texttrack',
135                // 'stylesheet',
136                // 'ping'
137            ];
138
139            // 过滤掉不需要的资源类型
140            if (blockedResourceTypes.includes(resourceType)) {
141                request.abort();
142            } else {
143                request.continue();
144            }
145        });
146        page.on('response', async (response) => {
147            const request = response.request();
148            const url = request.url();
149            if (await this.shouldInterceptRequest(url, request)) {
150                try {
151                    let responseBody = await response.json();
152                    await this.processResponseData(responseBody, interceptedData);
153                } catch (error) {
154                    // console.error(`Error fetching data: `, error);
155                }
156            }
157        });
158    }
159
160    async processResponseData(responseBody, interceptedData) {
161        let currentData = [];
162
163        // 每次处理 50 条数据
164        let list = responseBody?.dentists || [];
165        for (let i = 0; i < list.length; i += 50) {
166            let batchData = list.slice(i, i + 50);
167            batchData?.forEach((item) => {
168                if (item) {
169                    let data = {
170                        searchUrl: this.searchUrl,
171                        ...item
172                    };
173                    data.profiledentistDetailUrlUrl = 'https://www.dentalplans.com/' + item?.dentistDetailUrl;
174                    currentData.push(data);
175                    interceptedData.push(data);
176                }
177            });
178            
179            let limit = false;
180            // 如果超过最大数量,截断currentData
181            if (interceptedData.length > this.maxItems) {
182                const overflow = interceptedData.length - this.maxItems;
183                currentData = currentData.slice(0, -overflow);
184                interceptedData = interceptedData.slice(0, this.maxItems);
185                limit = true;
186            }
187    
188            if (currentData.length > 0) {
189                console.log(`Saved ${currentData.length} items`);
190                await Actor.pushData(currentData);
191            }
192
193            if (limit) {
194                break;
195            }
196
197        }
198        
199        
200    }
201
202    async shouldInterceptRequest(url, request) {
203        if (url.includes('/proxy/dentist/v1/search/') && request.method() === 'GET') {
204            
205            try {
206                let payload = {};
207                const postData = await request.postData();
208                if (postData) {
209                    try {
210                        // 尝试解析为 JSON
211                        const jsonData = JSON.parse(postData);
212                        payload = jsonData;
213                    } catch (e) {
214                        // 如果不是 JSON,则按 URL 编码处理
215                        const parsedData = {};
216                        const searchParams = new URLSearchParams(postData);
217                        for (const [key, value] of searchParams) {
218                            parsedData[key] = value;
219                        }
220                        payload = parsedData;
221                    }
222                } else {
223                }
224                // return payload?.operationName === 'getReviews';
225                return true;
226            } catch (error) {
227                console.error('Error parsing POST data:', error);
228            }
229        }
230        return false;
231    }
232
233    async scrollPage(page) {
234        await page.evaluate(() => {
235            document.querySelector('a[data-testid="paginator-navigation-button"]')?.click();
236            // document.querySelector('a[data-test="pagination-next"]')?.click();
237            // window.scrollTo(0, document.querySelector('div[data-test-id="profile-followers-feed"]')?.scrollHeight + 100)
238            // window.scrollTo(0, document.body.scrollHeight + 100)
239            // document.querySelector('div[data-test-id="profile-following"]')?.lastChild?.firstChild?.click()
240
241            // 点击下一页
242            // document.querySelector('a.next_page')?.click();
243            
244            // const scrollHeight = document.body.scrollHeight;
245            // const viewportHeight = window.innerHeight;
246            // const scrollSteps = Math.floor(Math.random() * 3) + 3; // 随机3-5步
247            // const stepSize = (scrollHeight - viewportHeight) / scrollSteps;
248            
249            // let currentScroll = 0;
250            // const scrollInterval = setInterval(() => {
251            //     if (currentScroll >= scrollHeight - viewportHeight) {
252            //         clearInterval(scrollInterval);
253            //         return;
254            //     }
255            //     currentScroll += stepSize + (Math.random() * 100 - 50); // 添加一些随机性
256            //     window.scrollTo(0, currentScroll);
257            // }, 100 + Math.random() * 200); // 随机间隔100-300毫秒
258        });
259    }
260
261    // 在滚动和其他操作之间添加随机延迟
262    async randomDelay(min = 1000, max = 3000) {
263        const delay = Math.floor(Math.random() * (max - min + 1) + min);
264        await new Promise(resolve => setTimeout(resolve, delay));
265    }
266
267
268}
269
270
271await Actor.init();
272
273Actor.main(async () => {
274    const input = await Actor.getInput();
275    // const input = {
276    //     "searchUrls": [
277    //         "https://www.dentalplans.com/dentist-search-results/?zip=90001&searchTerm="
278    //     ],
279    //     "maxItems": 130
280    // };
281    const crawler = new DentalplansDentistScraper();
282    await crawler.run(input);
283});

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

# This file tells Git which files shouldn't be added to source control
.DS_Store
.idea
dist
node_modules
apify_storage
storage/*
!storage/key_value_stores
storage/key_value_stores/*
!storage/key_value_stores/default
storage/key_value_stores/default/*
!storage/key_value_stores/default/INPUT.json

{
    "name": "js-scrape-single-page",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
		"apify": "^3.2.5",
		"crawlee": "^3.11.5",
		"puppeteer": "^23.5.0",
		"puppeteer-core": "^23.5.0",
		"puppeteer-extra": "^3.3.6",
		"random-useragent": "^0.5.0",
        "rebrowser-puppeteer": "^23.10.3",
		"rebrowser-puppeteer-core": "^23.10.3"
    },
    "scripts": {
        "start": "node ./src/main.js",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}