Doctolib

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4# Replace '<YOUR_API_TOKEN>' with your token.
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7# Prepare the Actor input
8run_input = {
9    "startUrls": [{ "url": "https://www.doctolib.fr/infectiologue/75001-paris" }],
10    "pageFunction": """async function pageFunction(context) {
11
12    let data = {}
13    let userData = context.request.userData
14    data.url = context.request.url
15
16    const isDoctorProfile = userData && userData.label === 'doctor'
17    let isProbablyDoctorProfile
18    if(!isDoctorProfile){
19        isProbablyDoctorProfile = await context.innerTextwrapper(context,'body.profiles, body.online_booking-drafts')
20    }
21    const isDoctorPage = isDoctorProfile || isProbablyDoctorProfile
22
23    data.isDoctorPage = isDoctorPage
24    
25    if(isDoctorPage){
26        context.log.info(`Doctor page ${isDoctorProfile ? 'from search' : '' } ${isProbablyDoctorProfile ? 'guessing' : '' }`);
27        data.nom = await context.page.locator('#main-content h1').innerText({timeout:6000})
28        data.tarif = await context.innerTextwrapper(context,'#payment_means')
29        data.horaire_contact = await context.innerTextwrapper(context,'#openings_and_contact')
30        data.description = await context.innerTextwrapper(context,'.dl-profile-bio')
31        data.specialite = await context.innerTextwrapper(context,'.dl-profile-header-speciality')
32        data.expertise = await context.innerTextwrapper(context,'#skills')
33        try{
34            data.website = await context.page.locator('.dl-profile-row-section div', { hasText: 'Website' }).locator('a').getAttribute('href',{timeout:2000})
35        }catch(e){
36            context.log.info('Website not found',e);     
37        }
38
39        try{
40            data.phones = await context.getPhones(data.horaire_contact)
41        }catch(e){
42            context.log.info('Phones not found',e);     
43        }
44        try{
45            data.image = await context.page.locator('.dl-profile img').first().getAttribute('src',{timeout:2000})
46            if(data.image.startsWith('/')){ data.image = 'https:' + data.image}
47        }catch(e){
48            context.log.info('Image not found',e);     
49        }        
50    }else{
51        context.log.info('we are not on a doctor page: so a search or pagination page.');
52        data.message = 'you can remove these rows in the settings with \"hideSearchPages\" '
53        userData.label = 'doctor';
54        const elements = context.page.locator('.search-result-card a[href]');
55        const links = await elements.evaluateAll(elems => elems.map(elem => elem.getAttribute('href')));
56        let extenstion = 'fr'
57        if(context.request.url.includes('doctolib.de')){ extenstion = 'de' }
58        if(context.request.url.includes('doctolib.it')){ extenstion = 'it' }
59        links.forEach(async link => {
60            if(link.startsWith('/')){ link = `https://www.doctolib.${extenstion}${link}` }
61            await context.enqueueRequest(link, userData , true);
62        })
63
64    }
65    context.log.info(`ending this page now`);
66
67    return data;
68}
69""",
70}
71
72# Run the Actor and wait for it to finish
73run = client.actor("anchor/doctolib").call(run_input=run_input)
74
75# Fetch and print Actor results from the run's dataset (if there are any)
76print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
77for item in client.dataset(run["defaultDatasetId"]).iterate_items():
78    print(item)
79
80# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start