Doctolib

$echo '{
<  "startUrls": [
<    {
<      "url": "https://www.doctolib.fr/infectiologue/75001-paris"
<    }
<  ],
<  "pageFunction": "async function pageFunction(context) {\\n\\n    let data = {}\\n    let userData = context.request.userData\\n    data.url = context.request.url\\n\\n    const isDoctorProfile = userData && userData.label === '\''doctor'\''\\n    let isProbablyDoctorProfile\\n    if(!isDoctorProfile){\\n        isProbablyDoctorProfile = await context.innerTextwrapper(context,'\''body.profiles, body.online_booking-drafts'\'')\\n    }\\n    const isDoctorPage = isDoctorProfile || isProbablyDoctorProfile\\n\\n    data.isDoctorPage = isDoctorPage\\n    \\n    if(isDoctorPage){\\n        context.log.info(`Doctor page ${isDoctorProfile ? '\''from search'\'' : '\'''\'' } ${isProbablyDoctorProfile ? '\''guessing'\'' : '\'''\'' }`);\\n        data.nom = await context.page.locator('\''#main-content h1'\'').innerText({timeout:6000})\\n        data.tarif = await context.innerTextwrapper(context,'\''#payment_means'\'')\\n        data.horaire_contact = await context.innerTextwrapper(context,'\''#openings_and_contact'\'')\\n        data.description = await context.innerTextwrapper(context,'\''.dl-profile-bio'\'')\\n        data.specialite = await context.innerTextwrapper(context,'\''.dl-profile-header-speciality'\'')\\n        data.expertise = await context.innerTextwrapper(context,'\''#skills'\'')\\n        try{\\n            data.website = await context.page.locator('\''.dl-profile-row-section div'\'', { hasText: '\''Website'\'' }).locator('\''a'\'').getAttribute('\''href'\'',{timeout:2000})\\n        }catch(e){\\n            context.log.info('\''Website not found'\'',e);     \\n        }\\n\\n        try{\\n            data.phones = await context.getPhones(data.horaire_contact)\\n        }catch(e){\\n            context.log.info('\''Phones not found'\'',e);     \\n        }\\n        try{\\n            data.image = await context.page.locator('\''.dl-profile img'\'').first().getAttribute('\''src'\'',{timeout:2000})\\n            if(data.image.startsWith('\''/'\'')){ data.image = '\''https:'\'' + data.image}\\n        }catch(e){\\n            context.log.info('\''Image not found'\'',e);     \\n        }        \\n    }else{\\n        context.log.info('\''we are not on a doctor page: so a search or pagination page.'\'');\\n        data.message = '\''you can remove these rows in the settings with \\"hideSearchPages\\" '\''\\n        userData.label = '\''doctor'\'';\\n        const elements = context.page.locator('\''.search-result-card a[href]'\'');\\n        const links = await elements.evaluateAll(elems => elems.map(elem => elem.getAttribute('\''href'\'')));\\n        let extenstion = '\''fr'\''\\n        if(context.request.url.includes('\''doctolib.de'\'')){ extenstion = '\''de'\'' }\\n        if(context.request.url.includes('\''doctolib.it'\'')){ extenstion = '\''it'\'' }\\n        links.forEach(async link => {\\n            if(link.startsWith('\''/'\'')){ link = `https://www.doctolib.${extenstion}${link}` }\\n            await context.enqueueRequest(link, userData , true);\\n        })\\n\\n    }\\n    context.log.info(`ending this page now`);\\n\\n    return data;\\n}\\n"
<}' |
<apify call anchor/doctolib --silent --output-dataset