ccppi/comparis-scrapper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

main file

Browse Source
This commit is contained in:
ccppi 2024-04-03 08:50:24 +02:00
parent aaff6694fd
commit 6598218abe
2 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
main.py Normal file
View File

@ -0,0 +1,5 @@
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)

14
scrap.py
View File

@ -47,13 +47,19 @@ def page_iterator(base_url,main_container_type,main_container_class,next_type,ne
#url gets href param, text gets textparam stripped and formated #url gets href param, text gets textparam stripped and formated
def filter(data,type_t,class_t,type_content): def filter(data,type_t,class_t,type_content):
text=[]
url=[]
for entry in data: for entry in data:
item = entry.find(type_t,class_=class_t) item = entry.find_all(type_t,class_=class_t)
if item != None: if item != None:
if type_content == "url": if type_content == "url":
return item.get("href") for it in item:
if type_of_sub_content == "text": url.append(it.get("href"))
return item.text.strip() return url
if type_content == "text":
for it in item:
text.append(it.text.strip())
return text
else: else:
return item return item
if item == None: if item == None: