Web gratte coronavirus de parcelles interactives

modifier: strong> Structure et code nécessitaient des modifications aussi p>

import requests
from bs4 import BeautifulSoup 
import json
#import dirtyjson
import js2xml
import pyjsparser

# --- functions ---

def test_eval(script):
    print('\n--- eval ---\n')

    # chart values
    text = script.split('data: [', 1)[1] # beginning
    text = text.split(']', 1)[0] # end
    values = eval(text)  # it creates tuple
    print(values)

    # title 
    # I split `yAxis` because there is other `title` without text
    # I split beginning in few steps because text may have different indentations (different number of spaces)
    # (you could use regex to split in one step)
    text = script.split("title: {\n", 1)[1] # beginning
    text = text.split("text: '", 1)[1] # beginning
    title = text.split("'", 1)[0] # end
    print('\ntitle:', title)

    text = script.split("yAxis: {\n", 1)[1] # beginning
    text = text.split("title: {\n", 1)[1] # beginning
    text = text.split("text: '", 1)[1] # beginning
    title = text.split("'", 1)[0] # end
    print('\ntitle:', title)

def test_json(script):
    print('\n--- json ---\n')

    # chart values
    text = script.split('data: [', 1)[1] # beginning
    text = text.split(']', 1)[0] # end
    text = '[' + text + ']' # create correct JSON data
    values = json.loads(text) # this time doesn't need `dirtyjson`
    print(values)

    # title
    # I split `yAxis` because there is other `title` without text
    # I split beginning in few steps because text may have different indentations (different number of spaces)
    # (you could use regex to split in one step)
    text = script.split("title: {\n", 1)[1] # beginning
    text = text.split("text: '", 1)[1] # beginning
    title = text.split("'", 1)[0] # end
    print('\ntitle:', title)

    text = script.split("yAxis: {\n", 1)[1] # beginning
    text = text.split("title: {\n", 1)[1] # beginning
    text = text.split("text: '", 1)[1] # beginning
    title = text.split("'", 1)[0] # end
    print('\ntitle:', title)

def test_js2xml(script):
    print('\n--- js2xml ---\n')

    data = js2xml.parse(script)

    # chart values (short and nice path)
    values = data.xpath('//property[@name="data"]//number/@value')
    #values = [int(x) for x in values] # it may need to convert to int() or float()
    #values = [float(x) for x in values] # it may need to convert to int() or float()
    print(values)

    # title (short and nice path)
    #print(js2xml.pretty_print(data.xpath('//property[@name="title"]')[0]))
    #title = data.xpath('//property[@name="title"]//string/text()')
    #print(js2xml.pretty_print(data.xpath('//property[@name="yAxis"]//property[@name="title"]')[0]))

    title = data.xpath('//property[@name="title"]//string/text()')
    title = title[0]
    print('\ntitle:', title)

    title = data.xpath('//property[@name="yAxis"]//property[@name="title"]//string/text()')
    title = title[0]
    print('\ntitle:', title)

def test_pyjsparser(script):
    print('\n--- pyjsparser ---\n')

    data = pyjsparser.parse(script)

    print("body's number:", len(data['body']))

    for number, body in enumerate(data['body']):
        if (body['type'] == 'ExpressionStatement'
            and body['expression']['callee']['object']['name'] == 'Highcharts'
            and len(body['expression']['arguments']) > 1):

            arguments = body['expression']['arguments']
            #print(json.dumps(values, indent=2))
            for properties in arguments[1]['properties']:
                #print('name: >{}<'.format(p['key']['name']))
                if properties['key']['name'] == 'series':
                    values = properties['value']['elements'][0]
                    values = values['properties'][-1]
                    values = values['value']['elements'] # a lot of work to find it
                    #print(json.dumps(values, indent=2))

                    values = [x['value'] for x in values]
                    print(values)

    # title (very complicated path) 
    # It needs more work to find correct indexes to get title
    # so I skip this part as too complex.

# --- main ---

url= 'https://www.worldometers.info/coronavirus/#countries'

r = requests.get(url)
#print(r.text)
soup = BeautifulSoup(r.text, "html.parser")

all_scripts = soup.find_all('script')
print('number of scripts:', len(all_scripts))

for number, script in enumerate(all_scripts):

    #if 'data: [' in script.text:
    if 'Highcharts.chart' in script.text:
        print('\n=== script:', number, '===\n')
        test_eval(script.text)
        test_json(script.text)
        test_js2xml(script.text)
        test_pyjsparser(script.text)