wiki-victory.py

import requests
import pandas as pd
from bs4 import BeautifulSoup

url_base = "https://en.wikipedia.org/wiki/Napoleon"

soup_base = BeautifulSoup(requests.get(url_base).content, "lxml")

links = soup_base.find("div", {"class": "navbox"}).find_all("li")

list = []
for index, link in enumerate(links, 1):
    try:
        dict_battle = {}
        lien = f"https://en.wikipedia.org{link.find('a')['href']}"
        # print(lien)
        soup_link = BeautifulSoup(requests.get(lien).content, "lxml")
        try:
            dict_battle["Name EN"] = soup_link.find(
                "h1", {"class": "firstHeading"}
            ).text
            text = [
                t.findNext("td").text.strip() for t in soup_link.find_all(text="Result")
            ]
            # print(f"Url {lien}, {text}")
            dict_battle["Result EN"] = text
            dict_battle["URL EN"] = lien
            try:
                lien_fr = soup_link.find("li", {"class": "interwiki-fr"}).find("a")[
                    "href"
                ]
                soup_link_fr = BeautifulSoup(requests.get(lien_fr).content, "lxml")
                dict_battle["Name FR"] = soup_link_fr.find(
                    "h1", {"class": "firstHeading"}
                ).text
                text_fr = [
                    t.findNext("td").text.strip()
                    for t in soup_link_fr.find_all("th")
                    if "Issue" in t.text
                ]
                # print(f"Url {lien_fr}, {text_fr}")
                dict_battle["Result FR"] = text_fr
                dict_battle["URL FR"] = lien_fr
            except Exception as e:
                print(f"Lien français non trouvé : {e}")
        except Exception as e:
            print(f"Balise non trouvée : {e}")
        list.append(dict_battle)
        print(f"{index}, {dict_battle}")
    except Exception as e:
        print(f"Pas possible de scraper : {e}")

df = pd.DataFrame(list)
df.to_csv("results.csv", sep="\t")