Merge pull request #508 from lalalaurentiu/main

Refactor code
peviitor-ro · Feb 15, 2024 · 781a8db · 781a8db
2 parents 34c40c5 + 303dd18
commit 781a8db
Show file tree

Hide file tree

Showing 8 changed files with 172 additions and 181 deletions.
diff --git a/sites/svn.py b/sites/svn.py
@@ -1,5 +1,11 @@
 from scraper.Scraper import Scraper
-from utils import (publish, publish_logo, create_job, show_jobs, translate_city, acurate_city_and_county)
+from utils import (
+    publish,
+    publish_logo,
+    create_job,
+    show_jobs,
+    translate_city
+)
 from getCounty import get_county, remove_diacritics
 
 
@@ -10,44 +16,48 @@ def remove_umlaut(string):
     :return: unumlauted string
     """
 
-    t = '\u0083'
-    a = '\u00c4\u0083'
-    aa = '\u00c3\u00a2'
+    t = "\u0083"
+    a = "\u00c4\u0083"
+    aa = "\u00c3\u00a2"
+
+    string = string.replace(t, "t")
+    string = string.replace(a, "a")
+    string = string.replace(aa, "a")
 
-    string = string.replace(t, 't')
-    string = string.replace(a, 'a')
-    string = string.replace(aa, 'a')
-
     return string
 
-company = 'SVN'
-url = 'https://jobs.svn.ro/posturi-vacante.html'
+
+company = "SVN"
+url = "https://jobs.svn.ro/posturi-vacante.html"
 
 scraper = Scraper()
 scraper.get_from_url(url)
 
 jobs = []
 
-jobs_elements = scraper.find('div', class_='jobs').find_all('div', class_='job')
+jobs_elements = scraper.find("div", class_="jobs").find_all("div", class_="job")
 
 for job in jobs_elements:
-    job_title = remove_diacritics(job.find('h3').text.encode(
-        'raw_unicode_escape').decode('utf-8'))
-    job_link='https://jobs.svn.ro' + job.find('a')['href']
-    city=translate_city(job.find('ul').find_all('li')[-1].text).replace("È", "s")
+    job_title = remove_diacritics(
+        job.find("h3").text.encode("raw_unicode_escape").decode("utf-8")
+    )
+    job_link = "https://jobs.svn.ro" + job.find("a")["href"]
+    city = translate_city(job.find("ul").find_all("li")[-1].text).replace("È", "s")
     county = get_county(city)
 
-    jobs.append(create_job(
-        job_title=job_title,
-        job_link=job_link,
-        company=company,
-        country="Romania",
-        city=city,
-        county=county,
-    ))
+    jobs.append(
+        create_job(
+            job_title=job_title,
+            job_link=job_link,
+            company=company,
+            country="Romania",
+            city=city,
+            county=county,
+        )
+    )
+
 
-for version in [1,4]:
-    publish(version, company, jobs, 'APIKEY')
+publish(4, company, jobs, "APIKEY")
 
-publish_logo(company, 'https://www.svn.ro/assets/images/logo/3.png')
-show_jobs(jobs)
+publish_logo(company, "https://www.svn.ro/assets/images/logo/3.png")
+show_jobs(jobs)
diff --git a/sites/synevo.py b/sites/synevo.py
@@ -1,7 +1,6 @@
-from scraper_peviitor import Scraper, Rules, loadingData
-import json
+from scraper_peviitor import Scraper, Rules
 from getCounty import get_county, remove_diacritics
-from utils import translate_city
+from utils import translate_city, publish, publish_logo, show_jobs
 
 # Cream o instanta a clasei Scraper
 scraper = Scraper("https://www.synevo.ro/cariere/")
@@ -30,36 +29,41 @@
         job_title = rules.getTag("h1", {"class": "entry-title"}).text
         # Daca sunt mai multe orase le impartim in lista
         # try :
-        locations = rules.getTag(
-            "div", {"class": "jobs-info-city"}).find("b").text.split(",")
+        locations = (
+            rules.getTag("div", {"class": "jobs-info-city"}).find("b").text.split(",")
+        )
 
         cities = list()
         counties = set()
 
         for city in locations:
             if "Chiajna" in city:
                 city = "Chiajna"
+            elif "Laborator Monza" in city:
+                city = "Bucuresti"
             else:
-                city = translate_city(
-                    remove_diacritics(city.strip())
-                )
+                city = translate_city(remove_diacritics(city.strip()))
 
             cities.append(city)
             counties.add(get_county(city))
 
         # Cream un dictionar cu jobul si il adaugam in lista finala
 
-        finaljobs.append({
-            "job_title": job_title,
-            "job_link": scraper.url,
-            "company": company.get("company"),
-            "country": "Romania",
-            "city": cities,
-            "county": list(counties),
-        })
+        finaljobs.append(
+            {
+                "job_title": job_title,
+                "job_link": scraper.url,
+                "company": company.get("company"),
+                "country": "Romania",
+                "city": cities,
+                "county": list(counties),
+            }
+        )
 
-# #Afisam numarul total de joburi
-print(json.dumps(finaljobs, indent=4))
 
-# #Incarcam datele in baza de date
-loadingData(finaljobs, company.get("company"))
+publish(4, company.get("company"), finaljobs, "APIKEY")
+
+logourl = "https://www.synevo.ro/wp-content/themes/synevo-sage/dist/images/synevo-logo_6edc429f.svg"
+publish_logo(company.get("company"), logourl)
+
+show_jobs(finaljobs)
diff --git a/sites/tbibank.py b/sites/tbibank.py
@@ -1,6 +1,6 @@
 from scraper.Scraper import Scraper
 import json
-from utils import show_jobs, translate_city, publish
+from utils import show_jobs, translate_city, publish, publish_logo
 from getCounty import get_county
 
 url = "https://tbibank.ro/cariere/"
@@ -27,7 +27,7 @@
         "job_link": job_link,
         "company": company,
         "country": country,
-        "remote": remote
+        "remote": remote,
     }
 
     if country == "Romania":
@@ -41,7 +41,10 @@
 
     finalJobs.append(job_obj)
 
-show_jobs(finalJobs)
 
-for version in [1, 4]:
-    publish(version, company, finalJobs, 'APIKEY')
+publish(4, company, finalJobs, "APIKEY")
+
+logoUrl = "https://tbibank.ro/wp-content/themes/Avada-child-bg/assets/images/tbi-layout/logo/new-logo.svg"
+publish_logo(company, logoUrl)
+
+show_jobs(finalJobs)
diff --git a/sites/teleperformance.py b/sites/teleperformance.py
@@ -1,43 +1,29 @@
-from scraper_peviitor import Scraper, loadingData
-import uuid
-import json
+from scraper_peviitor import Scraper
+from utils import publish, publish_logo, show_jobs, translate_city
+from getCounty import get_county
 
 apiUrl = "https://www.teleperformance.com/Umbraco/Api/Careers/GetCareersBase?node=13761&country=Romania&pageSize=100"
 
 company = {"company": "Teleperformance"}
-finalJobs = list()
 
 scraper = Scraper(apiUrl)
-
 jobs = scraper.getJson().get("resultado")
 
-for job in jobs:
-    id = uuid.uuid4()
-    job_title = job.get("title")
-    job_link = job.get("url")
-    city = job.get("location")
-
-    finalJobs.append({
-        "id": str(id),
-        "job_title": job_title,
-        "job_link": job_link,
+finalJobs = [
+    {
+        "job_title": job.get("title"),
+        "job_link": job.get("url"),
         "company": company.get("company"),
         "country": "Romania",
-        "city": city
-    })
-
-print(json.dumps(finalJobs, indent=4))
+        "city": translate_city(job.get("location")),
+        "county": get_county(translate_city(job.get("location"))),
+    }
+    for job in jobs
+]
 
-loadingData(finalJobs, company.get("company"))
+publish(4, company.get("company"), finalJobs, "APIKEY")
 
 logoUrl = "https://www.teleperformance.com/media/yn5lcxbl/tp-main-logo-svg.svg"
+publish_logo(company.get("company"), logoUrl)
 
-scraper.session.headers.update({
-    "Content-Type": "application/json",
-})
-scraper.post( "https://api.peviitor.ro/v1/logo/add/" ,json.dumps([
-    {
-        "id":company.get("company"),
-        "logo":logoUrl
-    }
-]))
+show_jobs(finalJobs)
diff --git a/sites/telusinternational.py b/sites/telusinternational.py
@@ -1,31 +1,31 @@
 from scraper.Scraper import Scraper
-from utils import (publish, publish_logo, show_jobs)
-
+from utils import publish, publish_logo, show_jobs
 
 url = "https://jobs.telusinternational.com/en_US/careers/Romania?source=TI+website&amp%3Btags=telus_main_website&listFilterMode=1&2947=5170&2947_format=4626"
 
 company = "TelusInternational"
-finalJobs = list()
 
 scraper = Scraper()
 scraper.get_from_url(url, verify=False)
 
 jobs = scraper.find_all("li", {"class": "listSingleColumnItem"})
 
-for job in jobs:
-    job_title = job.find("h3").text.strip()
-    job_link = job.find("h3").find("a").get("href")
-
-    finalJobs.append({
-        "job_title": job_title,
-        "job_link": job_link,
+finalJobs = [
+    {
+        "job_title": job.find("h3").text.strip(),
+        "job_link": job.find("h3").find("a").get("href"),
         "company": company,
         "country": "Romania",
         "city": "Bucuresti",
-        "county": "Bucuresti"
-    })
+        "county": "Bucuresti",
+    }
+    for job in jobs
+]
+
 
-for version in [1,4]:
-    publish(version, company, finalJobs, 'APIKEY')
-publish_logo(company, "https://jobs.telusinternational.com/portal/11/images/logo_telus-international_header-v2.svg")
+publish(4, company, finalJobs, "APIKEY")
+publish_logo(
+    company,
+    "https://jobs.telusinternational.com/portal/11/images/logo_telus-international_header-v2.svg",
+)
 show_jobs(finalJobs)
diff --git a/sites/thalesgroup.py b/sites/thalesgroup.py
@@ -1,6 +1,6 @@
-from scraper_peviitor import Scraper, loadingData
-import uuid
-import json
+from scraper_peviitor import Scraper
+from utils import publish, publish_logo, show_jobs, translate_city
+from getCounty import get_county
 
 apiUrl = "https://thales.wd3.myworkdayjobs.com/wday/cxs/thales/Careers/jobs"
 
@@ -14,7 +14,12 @@
     "Content-Type": "application/json",
 }
 
-data = {"appliedFacets":{"locationCountry":["f2e609fe92974a55a05fc1cdc2852122"]},"limit":20,"offset":0,"searchText":""}
+data = {
+    "appliedFacets": {"locationCountry": ["f2e609fe92974a55a05fc1cdc2852122"]},
+    "limit": 20,
+    "offset": 0,
+    "searchText": "",
+}
 
 scraper.session.headers.update(headers)
 
@@ -26,33 +31,27 @@
     data["offset"] = num
     jobs = scraper.post(apiUrl, json=data).json().get("jobPostings")
     for job in jobs:
-        id = uuid.uuid4()
         job_title = job.get("title")
-        job_link = "https://thales.wd3.myworkdayjobs.com/en-US/Careers" + job.get("externalPath")
-        city = job.get("locationsText").split(",")[0]
-
-        finalJobs.append({
-            "id": str(id),
-            "job_title": job_title,
-            "job_link": job_link,
-            "company": company.get("company"),
-            "country": "Romania",
-            "city": city
-        })
-
-print(json.dumps(finalJobs, indent=4))
-
-loadingData(finalJobs, company.get("company"))
+        job_link = "https://thales.wd3.myworkdayjobs.com/en-US/Careers" + job.get(
+            "externalPath"
+        )
+        city = translate_city(job.get("locationsText").split(",")[0])
+        county = get_county(city)
+
+        finalJobs.append(
+            {
+                "job_title": job_title,
+                "job_link": job_link,
+                "company": company.get("company"),
+                "country": "Romania",
+                "city": city,
+                "county": county,
+            }
+        )
+
+publish(4, company.get("company"), finalJobs, "APIKEY")
 
 logoUrl = "https://upload.wikimedia.org/wikipedia/commons/thumb/2/21/Thales_Logo.svg/484px-Thales_Logo.svg.png?20210518101610"
+publish_logo(company.get("company"), logoUrl)
 
-scraper.session.headers.update({
-    "Content-Type": "application/json",
-})
-scraper.post( "https://api.peviitor.ro/v1/logo/add/" ,json.dumps([
-    {
-        "id":company.get("company"),
-        "logo":logoUrl
-    }
-]))
-
+show_jobs(finalJobs)