Last active
June 18, 2021 00:59
-
-
Save shocknawe/4974fefedba3f80e349fcd96b5b67493 to your computer and use it in GitHub Desktop.
Inline scrapper for grip events
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Grab from network call headers | |
var X_AUTHORIZATION = "2878e4b1-77b0-48f0-bbd2-e25e31fd345b"; | |
var getAllPersonIds = () => { | |
var items = document.querySelectorAll("app-network article"); | |
items = Array.from(items); | |
return items.map((item) => { | |
let link = item.querySelector(".media-content a[data-test]"); | |
let itemId = link.getAttribute("data-test"); | |
itemId = itemId.replace("thingId", ""); | |
return itemId; | |
}); | |
}; | |
var getPersonData = async (personId) => { | |
try { | |
let url = `https://api-prod.intros.at/1/container/3168/thing/${personId}`; | |
let response = await fetch(url, { | |
method: "GET", | |
headers: { | |
"Content-Type": "application/json", | |
"login-source": "web", | |
"x-authorization": X_AUTHORIZATION, | |
"x-grip-version": "Web/7.8.1", | |
}, | |
}); | |
var data = await response.json(); | |
var contactData = await getPersonContacts(personId); | |
data.data.email = contactData.data.email; | |
data.data.phone_number = contactData.data.phone_number; | |
return data; | |
} catch (err) { | |
throw err; | |
} | |
}; | |
var getPersonContacts = async (personId) => { | |
try { | |
let url = `https://api-prod.intros.at/1/container/3168/thing/${personId}/contact_details`; | |
let response = await fetch(url, { | |
method: "GET", | |
headers: { | |
"Content-Type": "application/json", | |
"login-source": "web", | |
"x-authorization": X_AUTHORIZATION, | |
"x-grip-version": "Web/7.8.1", | |
}, | |
}); | |
var data = await response.json(); | |
return data; | |
} catch (err) { | |
throw err; | |
} | |
}; | |
var getAllPersonData = async () => { | |
var personIds = getAllPersonIds(); | |
// var personIds = ["5071963","5103063", "5130480"]; // attendees | |
// var personIds = ["5093035","5093059"]; // speakers | |
// var personIds = ["5136942"]; // sponsor representative | |
let personPromises = personIds.map((id) => getPersonData(id)); | |
return await Promise.all(personPromises); | |
}; | |
var cleanString = (str) => { | |
let returnStr = str; | |
returnStr = returnStr === null || returnStr === undefined ? "" : returnStr; | |
returnStr = "" + returnStr; | |
return returnStr; | |
}; | |
var formatItemAsHtmlRow = (item) => { | |
let { | |
id, | |
first_name, | |
last_name, | |
company_name, | |
job_title, | |
location, | |
email, | |
phone_number, | |
headline, | |
rtm_raw, | |
} = item.data; | |
let businessCategory = ""; | |
let businessLine = ""; | |
let businessCountry = ""; | |
if (rtm_raw) { | |
if (rtm_raw.country_code && rtm_raw.country_code.value) { | |
businessCountry = rtm_raw.country_code.value; | |
} | |
if (rtm_raw.business_category && rtm_raw.business_category.value) { | |
businessCategory = rtm_raw.business_category.value.join(", "); | |
} | |
if (rtm_raw.business_line && rtm_raw.business_line.value) { | |
businessLine = rtm_raw.business_line.value.join(", "); | |
} | |
} | |
return ` | |
<tr> | |
<td><a href="https://matchmaking.grip.events/insuretechconnectasia/app/profile/${id}">${id}</a></td> | |
<td>${first_name}</td> | |
<td>${last_name}</td> | |
<td>${company_name}</td> | |
<td>${job_title}</td> | |
<td>${location}</td> | |
<td>${businessCountry}</td> | |
<td>${businessCategory}</td> | |
<td>${businessLine}</td> | |
<td>${cleanString(email)}</td> | |
<td> ${cleanString(phone_number)}</td> | |
<td>${headline}</td> | |
</tr> | |
`; | |
}; | |
// copied from https://stackoverflow.com/a/27843359 | |
var exportToExcel = (data) => { | |
var htmls = data.map((item) => formatItemAsHtmlRow(item)).join(""); | |
var header = ` | |
<tr> | |
<td>Link to profile</td> | |
<td>First Name</td> | |
<td>Last Name</td> | |
<td>Company</td> | |
<td>Job Title</td> | |
<td>Location</td> | |
<td>Business Country</td> | |
<td>Business Category</td> | |
<td>Business Line</td> | |
<td>Email</td> | |
<td>Phone Number</td> | |
<td>Headline</td> | |
</tr>`; | |
var uri = "data:application/vnd.ms-excel;base64,"; | |
var template = | |
'<html xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:x="urn:schemas-microsoft-com:office:excel" xmlns="http://www.w3.org/TR/REC-html40"><head><!--[if gte mso 9]><xml><x:ExcelWorkbook><x:ExcelWorksheets><x:ExcelWorksheet><x:Name>{worksheet}</x:Name><x:WorksheetOptions><x:DisplayGridlines/></x:WorksheetOptions></x:ExcelWorksheet></x:ExcelWorksheets></x:ExcelWorkbook></xml><![endif]--></head><body><table>{table}</table></body></html>'; | |
var base64 = function (s) { | |
return window.btoa(unescape(encodeURIComponent(s))); | |
}; | |
var format = function (s, c) { | |
return s.replace(/{(\w+)}/g, function (m, p) { | |
return c[p]; | |
}); | |
}; | |
var ctx = { | |
worksheet: "Worksheet", | |
table: header + htmls, | |
}; | |
var link = document.createElement("a"); | |
link.download = "export.xls"; | |
link.href = uri + base64(format(template, ctx)); | |
link.click(); | |
}; | |
var scraper = async () => { | |
var data = await getAllPersonData(); | |
exportToExcel(data); | |
}; | |
scraper(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment