soidfj

main.py

@@ -1,5 +1,8 @@
 import scrap
-
-content = scrap.scrap("https://www.comparis.ch/immobilien/marktplatz/lenzburg/mieten",'div','css-1d60yla ehesakb4')
-content = scrap.filter(content,"p","Wohnung","text")
-print(content)
+from scrap import filter_type
+page = scrap.scrap("https://www.comparis.ch/immobilien/marktplatz/lenzburg/mieten",'div','css-1d60yla ehesakb4')
+#print(content)
+content2 = scrap.filter(page,'p',filter_type.text,"Wohnung",filter_type.href,5)
+print(content2)
+url = scrap.filter(page,'svg',filter_type.class_t,"fa-arrow-right",filter_type.href,0)
+print("url:",url)

scrap.py

@@ -4,27 +4,34 @@ import string
 import csv
 import numpy as np
 from bs4 import BeautifulSoup
+from enum import Enum
+
+class filter_type(Enum):
+    href = 1
+    text = 2
+    class_t = 3
 
 #returns all result for a html-element by class from a url
 def scrap(url,html_element,class_t):
     page = requests.get(url)
     soup = BeautifulSoup(page.content,"html.parser")
-    results = soup.find_all(html_element,class_=class_t)
-    print("class",class_t)
-    return results
+#    results = soup.find_all(html_element,class_=class_t)
+#    print("class",class_t)
+#    print("results:",results)
+    return soup
 
 #search for a "next button" or link given som DOM elements and returns the next url
-def page_iterator(base_url,main_container_type,main_container_class,next_type,next_class,string_parse):
+def page_iterator(base_url,next_type,next_class,parent_iteration,string_parse):
     found = False
 
     page = requests.get(base_url)
     soup = BeautifulSoup(page.content,"html.parser")
-    results = soup.find(main_container_type,class_=main_container_class)
-    if pages != None:
-        pages = results.text 
-    else:
-        print("found nothing on page")
-        return 0
+#    results = soup.find(main_container_type,class_=main_container_class)
+#    if pages != None:
+#        pages = results.text 
+#    else:
+#        print("found nothing on page")
+#        return 0
 
     next_url_names = soup.find_all(next_type,class_=next_class)
     if next_url_names != None:
@@ -46,22 +53,26 @@ def page_iterator(base_url,main_container_type,main_container_class,next_type,ne
         return 0
 
 #url gets href param, text gets textparam stripped and formated
-def filter(data,type_t,class_t,type_content):
-    text=[]
-    url=[]
-    for entry in data:
-        item = entry.find_all(type_t,class_=class_t)
-        if item != None:
-            if type_content == "url":
-                for it in item:
-                    url.append(it.get("href"))
-                return url
-            if type_content == "text":
-                for it in item:
-                     text.append(it.text.strip())
-                return text
+def filter(page,tag,search_by,search_string,to_extract,parent_iteration):
+    content=[]
+    if search_by == filter_type.class_t:
+        item = page.find_all(tag,class_=search_string)
+    if search_by == filter_type.text:
+        item = page.find_all(tag,string=search_string)
     else:
-                return item
+        print("filter_type not known: ",search_by)
+        return 0
+    if item != None:
+        for it in item:
+            for i in range(0,parent_iteration):
+                it = it.parent
+            if to_extract == filter_type.href:
+                content.append(it.get("href"))
+            if to_extract == filter_type.text:
+                content.append(it.string.strip())
+        return content
     if item == None:
+        print("No Item found")
         return 0
 
+