Forums

    from flask import Flask
from scrape import scrape

app = Flask(__name__)

@app.route("/")
def defaultData(country='india'):
    return scrape(country)

@app.route("/<country>")
def fetchdata(country='india'):
    return scrape(country)

    import json
import requests
from bs4 import BeautifulSoup

def scrape(country):
    country = country.lower().replace(' ', '-')
    res = requests.get('https://www.factmonster.com/world/countries/'+country)
    url_data = BeautifulSoup(res.text, 'html.parser')


    def data_heading_nolink(url_data):
        keys = ('Monetary unit', 'National name')
        result: dict = {}
        for j in keys:
            for i in url_data.find_all('p'):
                try:
                    if j in str(i):
                        result[j] = i.text.split(':')[1].strip()
                        break
                except IndexError as e:
                    result[j] = 'Failed to retrieve'
        return result


    def data_heading_link(url_data):
        keys = ('Capital', 'Language')
        result: dict = {}
        for j in keys:
            for i in url_data.find_all('p'):
                try:
                    if j in str(i):
                        result[j] = i.text.split(':')[1].split(',')[0].strip()
                        break
                    if 'Capital and largest' in str(i):
                        result['Largest city'] = result['Capital']
                except IndexError as e:
                    result[j] = 'Failed to retrieve'
        return result


    def get_map(url_data):
        map_code = str(url_data.select('.field_country_map')).split()
        for i in map_code:
            if 'src' in i:
                return('https://www.factmonster.com'+i[5:])
        return 'Map not found'


    info: dict = {}
    info.update(data_heading_nolink(url_data))
    info.update(data_heading_link(url_data))
    info['map']=get_map(url_data)

    counrty_json = json.dumps(info)
    return counrty_json

    Traceback (most recent call last):
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/flask/app.py", line 2528, in wsgi_app
    response = self.full_dispatch_request()
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/flask/app.py", line 1825, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/flask/app.py", line 1823, in full_dispatch_request
    rv = self.dispatch_request()
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/flask/app.py", line 1799, in dispatch_request
    return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
  File "/home/MyPythonServer608/country_data_fetching_API/server.py", line 12, in fetchdata
    return scrape(country)
  File "/home/MyPythonServer608/country_data_fetching_API/scrape.py", line 7, in scrape
    res = requests.get('https://www.factmonster.com/world/countries/'+country)
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/requests/api.py", line 73, in get
    return request("get", url, params=params, **kwargs)
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/requests/api.py", line 59, in request
    return session.request(method=method, url=url, **kwargs)
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/requests/sessions.py", line 587, in request
    resp = self.send(prep, **send_kwargs)
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/requests/sessions.py", line 701, in send
    r = adapter.send(request, **kwargs)
  File "/home/MyPythonServer608/.virtualenvs/my-virtualenv/lib/python3.10/site-packages/requests/adapters.py", line 559, in send
    raise ProxyError(e, request=request)
requests.exceptions.ProxyError: HTTPSConnectionPool(host='www.factmonster.com', port=443): Max retries exceeded with url: /world/countries/favicon.ico (Caused by ProxyError('Cannot connect to proxy.', OSError('Tunnel connection failed: 403 Forbidden')))

2023-02-25 14:27:59 [rule: 0] subject: path_info regexp: \.svgz$ action: addheader:Content-Encoding:gzip
2023-02-25 14:27:59 *** end of the internal routing table ***
2023-02-25 14:27:59 chdir() to /home/MyPythonServer608/
2023-02-25 14:27:59 your processes number limit is 128
2023-02-25 14:27:59 your memory page size is 4096 bytes
2023-02-25 14:27:59 detected max file descriptor number: 123456
2023-02-25 14:27:59 building mime-types dictionary from file /etc/mime.types...
2023-02-25 14:27:59 567 entry found
2023-02-25 14:27:59 lock engine: pthread robust mutexes
2023-02-25 14:27:59 thunder lock: disabled (you can enable it with --thunder-lock)
2023-02-25 14:27:59 uwsgi socket 0 bound to UNIX address /var/sockets/mypythonserver608.pythonanywhere.com/socket fd 3
2023-02-25 14:27:59 Python version: 3.10.5 (main, Jul 22 2022, 17:09:35) [GCC 9.4.0]
2023-02-25 14:27:59 PEP 405 virtualenv detected: /home/MyPythonServer608/.virtualenvs/my-virtualenv
2023-02-25 14:27:59 Set PythonHome to /home/MyPythonServer608/.virtualenvs/my-virtualenv
2023-02-25 14:27:59 *** Python threads support is disabled. You can enable it with --enable-threads ***
2023-02-25 14:27:59 Python main interpreter initialized at 0x55b37be84e60
2023-02-25 14:27:59 your server socket listen backlog is limited to 100 connections
2023-02-25 14:27:59 your mercy for graceful operations on workers is 60 seconds
2023-02-25 14:27:59 setting request body buffering size to 65536 bytes
2023-02-25 14:27:59 mapped 334256 bytes (326 KB) for 1 cores
2023-02-25 14:27:59 *** Operational MODE: single process ***
2023-02-25 14:27:59 initialized 38 metrics
2023-02-25 14:27:59 WSGI app 0 (mountpoint='') ready in 1 seconds on interpreter 0x55b37be84e60 pid: 1 (default app)
2023-02-25 14:27:59 *** uWSGI is running in multiple interpreter mode ***
2023-02-25 14:27:59 gracefully (RE)spawned uWSGI master process (pid: 1)
2023-02-25 14:27:59 spawned uWSGI worker 1 (pid: 2, cores: 1)
2023-02-25 14:27:59 metrics collector thread started
2023-02-25 14:27:59 spawned 2 offload threads for uWSGI worker 1
2023-02-25 14:28:00 announcing my loyalty to the Emperor...