Das deutsche Python-Forum

Code: Alles auswählen

import requests
from BeautifulSoup import BeautifulSoup as soup
import pprint

url = "http://de.wikipedia.org/wiki/Liste_der_chemischen_Elemente"
data = requests.get(url).text
soup = soup(data)

elemente = {}

for x in range(0, 250, 2):
    try:
        elemente[str(soup("td", {"align": "left"})[x].a.string)] = [
            str(soup("td", {"align": "right"})[x].string),
            str(soup("td", {"align": "right"})[x].string)
        ]
    except IndexError:
        continue

pprint.pprint(elemente)

Code: Alles auswählen

from collections import namedtuple
import requests
from bs4 import BeautifulSoup


Element = namedtuple(
    'Element', 'name symbol atomic_number weight density melt boil'
)


def parse_float(string):
    if not string.strip():
        return float('nan')
    if string.startswith(u'\N{MINUS SIGN}'):
        string = '-' + string[1:]
    return float(string.replace(',', '.'))


def parse_element_table(html_source):
    soup = BeautifulSoup(html_source)
    parsers = (
        unicode,
        unicode,
        int,
        parse_float,
        parse_float,
        parse_float,
        parse_float,
    )
    for row in soup.find('table', 'wikitable').tr.find_next_siblings('tr'):
        yield Element(*(p(c.text) for p, c in zip(parsers, row('td')[:7])))


def main():
    url = 'http://de.wikipedia.org/wiki/Liste_der_chemischen_Elemente'
    response = requests.get(url)
    elements = list(parse_element_table(response.text))
    print elements



if __name__ == '__main__':
    main()