2024-03-28 09:54:08 +00:00
|
|
|
#-*- coding: utf-8 -*-
|
|
|
|
import requests
|
|
|
|
import string
|
|
|
|
import csv
|
|
|
|
import numpy as np
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
|
|
|
#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)
|
2024-04-02 09:37:58 +00:00
|
|
|
print("class",class_t)
|
2024-03-28 09:54:08 +00:00
|
|
|
return results
|
|
|
|
|
|
|
|
#search for a "next button" or link given som DOM elements and returns the next url
|
2024-04-02 09:37:58 +00:00
|
|
|
def page_iterator(base_url,main_container_type,main_container_class,next_type,next_class,string_parse):
|
2024-03-28 09:54:08 +00:00
|
|
|
found = False
|
|
|
|
|
|
|
|
page = requests.get(base_url)
|
|
|
|
soup = BeautifulSoup(page.content,"html.parser")
|
|
|
|
results = soup.find(main_container_type,class_=main_container_class)
|
2024-04-02 09:37:58 +00:00
|
|
|
if pages != None:
|
|
|
|
pages = results.text
|
|
|
|
else:
|
|
|
|
print("found nothing on page")
|
|
|
|
return 0
|
2024-03-28 09:54:08 +00:00
|
|
|
|
|
|
|
next_url_names = soup.find_all(next_type,class_=next_class)
|
2024-04-02 09:37:58 +00:00
|
|
|
if next_url_names != None:
|
|
|
|
for i2 in next_url_names:
|
|
|
|
striped_string = i2.text.strip()
|
|
|
|
print(i2.text.strip(),"stripped:",striped_string)
|
|
|
|
# print("Printable characters?",striped_string.isprintable())
|
|
|
|
if (striped_string) == string_parse:
|
|
|
|
print(i2)
|
|
|
|
next_url = i2.get("href")
|
|
|
|
print("url of next site")
|
|
|
|
found = True
|
|
|
|
return next_url
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
found = False
|
2024-03-28 09:54:08 +00:00
|
|
|
if found == False:
|
|
|
|
print("No (more) elements found")
|
|
|
|
return 0
|
|
|
|
|
|
|
|
#url gets href param, text gets textparam stripped and formated
|
2024-04-02 09:37:58 +00:00
|
|
|
def filter(data,type_t,class_t,type_content):
|
2024-04-03 06:50:24 +00:00
|
|
|
text=[]
|
|
|
|
url=[]
|
2024-03-28 09:54:08 +00:00
|
|
|
for entry in data:
|
2024-04-03 06:50:24 +00:00
|
|
|
item = entry.find_all(type_t,class_=class_t)
|
2024-03-28 09:54:08 +00:00
|
|
|
if item != None:
|
|
|
|
if type_content == "url":
|
2024-04-03 06:50:24 +00:00
|
|
|
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
|
2024-03-28 09:54:08 +00:00
|
|
|
else:
|
|
|
|
return item
|
|
|
|
if item == None:
|
|
|
|
return 0
|
|
|
|
|