import json
input_json = """
[
{
"title":"Мобильный Телефон Xiaomi Redmi Note 8 (6+128Gb) Global IND",
"cost":"13.000 сом",
"link":"www.gadget.kg/catalog/telefony/xiaomi/3337"
},
{
"title":"Смарт Часы женские Bakeey H8",
"cost":"1.800 сом",
"link":"www.gadget.kg/catalog/gadzhety/smart-chasy-braslet..."
},
{
"title":"Смарт-часы Samsung Galaxy Watch R800 46mm",
"cost":"15.000 сом",
"link":"www.gadget.kg/catalog/gadzhety/smart-chasy-braslet..."
},
{
"title":"Смарт-часы Samsung Galaxy Watch R810 42mm",
"cost":"14.700 сом",
"link":"www.gadget.kg/catalog/gadzhety/smart-chasy-braslet..."
}
]
"""
input_dict = json.loads(input_json)
search_term = 'samsung'
output_dict = [x for x in input_dict if search_term in x['title'].lower()]
output_json = json.dumps(output_dict, indent=4, sort_keys=True, ensure_ascii=False)
print(output_json)[
{
"cost": "15.000 сом",
"link": "www.gadget.kg/catalog/gadzhety/smart-chasy-braslet...",
"title": "Смарт-часы Samsung Galaxy Watch R800 46mm"
},
{
"cost": "14.700 сом",
"link": "www.gadget.kg/catalog/gadzhety/smart-chasy-braslet...",
"title": "Смарт-часы Samsung Galaxy Watch R810 42mm"
}
]
import requests
from bs4 import BeautifulSoup
def get_html(site):
r = requests.get(site)
return r.text
def get_page_data(html): #sources
soup = BeautifulSoup(html, 'lxml') #(format_in, parser)
line = soup.find('table', id='theProxyList').find_all('tr') #resolve table
for tr in line:
td = tr.find_all('td')
if td == []:
continue
ip = td[1].text
port = td[2].text
country = td[3].text
anonym = td[4].text
types = td[5].text
time = td[6].text
data = {'ip': ip,
'Port': port,
'Country': country,
'Anonymize': anonym,
'Type': types,
'Time': time}
print(data)
def main():
url = 'http://foxtools.ru/Proxy'
get_page_data(get_html(url))
if __name__ == '__main__':
main()