From 4ede40c37c0c8e098a8c66923f2eaea5517a8861 Mon Sep 17 00:00:00 2001
From: ccppi <ccppi3@kolabnow.ch>
Date: Thu, 18 Jul 2024 11:26:13 +0200
Subject: [PATCH] - change search classes - change some to attributes -
 implement better debuging solution in finder()

---
 lib/conf          |  6 ++++++
 lib/helpers.py    | 19 +++++++++++++++----
 lib/scrap_jobs.py | 10 +++++-----
 3 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/lib/conf b/lib/conf
index f3928a3..0c824cd 100644
--- a/lib/conf
+++ b/lib/conf
@@ -1,3 +1,9 @@
+[jobs.ch_seilbahn]
+USER = NONE
+PW = NONE
+LOGINURL = NONE
+SCRAPURL = https://www.jobs.ch/en/vacancies/?term=seilbahn
+TAG = Seilbahn
 
 [jobagent.ch]
 USER = j.wyss@kolabnow.ch
diff --git a/lib/helpers.py b/lib/helpers.py
index 7e32428..3e39ff0 100644
--- a/lib/helpers.py
+++ b/lib/helpers.py
@@ -5,7 +5,7 @@ from enum import Enum
 import re
 from dateconverter import *
 from datetime import datetime
-DEBUG = False
+DEBUG = True
 
 def log(*s):
     if DEBUG:
@@ -35,10 +35,14 @@ months = [
     ('November','11'),
     ('December','12')]
 class item():
-    def __init__(self,tag,tag_content,index):
+    def __init__(self,tag,tag_content,index,name=None):
         self.tag = tag
         self.tag_content = tag_content
         self.index = index
+        if name is not None:
+            self.name = name
+        else:
+            self.name = "not defined"
 
 class job():
     def __init__(self,title,profession,company,location,date,description,link,tag,starred):
@@ -63,15 +67,22 @@ def finder(results,item,**modes):
     BASEURL = modes.get('BASEURL','')
     content = []
     i = item.index
+    log("name",item.name)
+    log("Item tag: ",item.tag)
     log("Modes:",modes)
-    
+    log("tag_content: ",item.tag_content) 
+
     for entry in results:
         if ATTRS==1:
             result = entry.findAll(item.tag,attrs=item.tag_content)
             log(item.tag_content)
         else:
             result = entry.findAll(item.tag,class_=item.tag_content)
-            log("found count count results:",len(result))
+            log("found count results:",len(result))
+            if item.name == "TITLE!!" and len(result) == 0 and  DEBUG == True:
+                for x in results:
+                    log(x)
+                    input()
         if result:
             log("theres a result")
             if i>(len(result)-1):
diff --git a/lib/scrap_jobs.py b/lib/scrap_jobs.py
index d99474a..b838b4e 100644
--- a/lib/scrap_jobs.py
+++ b/lib/scrap_jobs.py
@@ -1,5 +1,5 @@
 from helpers import *
-DEBUG = False
+DEBUG = True
 
 def log(*s):
     if DEBUG:
@@ -43,7 +43,7 @@ def scrap_jobs(url,entry,session):
     soup = BeautifulSoup(page.content,"html.parser")
     #print(soup.prettify())
 
-    results = soup.find_all("div",attrs={"data-feat":"searched_jobs"})
+    results = soup.find_all("div",attrs={'data-feat':'searched_jobs'})
     
     location_class = "P-sc-hyu5hk-0 Text__p2-sc-1lu7urs-10 Span-sc-1ybanni-0 Text__span-sc-1lu7urs-12 Text-sc-1lu7urs-13 jZCxUn"
     location = item("p",location_class,0)
@@ -53,14 +53,14 @@ def scrap_jobs(url,entry,session):
     company  = item("p",company_class,3)
     ar_company = finder(results,company,DEFAULT=1)
     
-    title = item("span","Span-sc-1ybanni-0 Text__span-sc-1lu7urs-12 Text-sc-1lu7urs-13 VacancyItem___StyledText2-sc-iugtv6-5 iaJYDR jlFpCz dMwMcR",0)
+    title = item("span","jlFpCz",0,"TITLE!!")
     ar_title = finder(results,title,DEFAULT=1)
 
     date = item("span","Span-sc-1ybanni-0 Text__span-sc-1lu7urs-12 Text-sc-1lu7urs-13 krGudM hUhFmL",0)
     ar_date = finder(results,date,CLEANDATE=1)
 
-    link = item("a","VacancyLink___StyledLink-sc-ufp08j-0",0)
-    ar_link = finder(results,link,LINK=1,BASEURL="https://jobs.ch")
+    link = item("a",{'data-cy' :'job-link'},0)
+    ar_link = finder(results,link,LINK=1,ATTRS=1,BASEURL="https://jobs.ch")
     
     tag = entry.tag#get from config
     return arrayToClass(ar_title,ar_company,ar_location,ar_date,ar_link,tag)