Web Scraping de Wikipedia avec Python

---

Grand fan de géographie, je voulais sauvegarder la page Wikipedia de chaque pays en PDF et toutes les imprimer afin de me confectionner une sorte d'encyclopédie sur le monde. Python m'a aidé à automatiser la tâche.

Le script suivant extrait la liste de tous les pays du monde de Wikipedia, obtient leurs URLs, et enregistre les pages en PDF:

        import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry
from bs4 import BeautifulSoup


# sessions helped me bypass errors when requesting web pages
session = requests.Session()
retry = Retry(connect=3, backoff_factor=0.5)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)

# get list of all countries
url_page = "https://en.wikipedia.org/wiki/List_of_sovereign_states"
r = session.get(url_page)
soup = BeautifulSoup(r.content, "html.parser")
countries_table = soup.find('table', {"class": "sortable wikitable"})
table_rows = countries_table.find_all('tr')
country_list = []

# for every country, get the link that will allow to scrape wiki's API for the PDF docs
for row in table_rows[4:]:
    data = row.find_all('td')
    try:        
        rough_link = data[0].find('a', href=True)
        link = rough_link['href']
        if link[0] == '#':
            pass
        else:
            country_name = link[6:]
            country_list.append(country_name)
    except:
        pass

# get the PDF documents
for country in country_list:
    base_url = 'https://en.wikipedia.org/api/rest_v1/page/pdf/'
    url = base_url + country
    myfile = requests.get(url, allow_redirects=True)
    destination = '../eBooks/Wikipedia countries' + country + '.pdf' # set destiation path, where PDF files will be saved
    open(destination, 'wb').write(myfile.content)