Exemple #1
0
def parseDesc():
    tournois = {}

    directory = os.listdir("webContent/desc/")
    for fileIn in directory:
        id_tournois = fileIn.split(".")[0]
        id_tournois = id_tournois.split("_")[1]
        tournoi = {}
        with open("webContent/desc/" + fileIn, mode='r',
                  encoding='utf-8') as fp:
            soup = BeautifulSoup(
                fp,
                'html.parser',
            )
        data = soup.find_all("span")
        for child in data:
            id_element = child.attrs['id']
            if (id_element):
                id_element_split = id_element.split("_")
                nb_element = len(id_element_split)
                if (nb_element > 0):
                    tag = id_element_split[nb_element - 1]
                    if (tag != "LabelTitre"):
                        tournoi[tag[5:]] = child.text
        tournois[id_tournois] = tournoi

    includes.saveInJSON(tournois, "tournois")
Exemple #2
0
def parseGrille():
    res = {}

    for filename in files:
        id_tournois = filename.split("_")[1].split(".")[0]
        titre = []
        file = open(directory + filename, mode="r", encoding="utf-8")
        soup = BeautifulSoup(file, 'html.parser')

        Titrelist = soup.table.find(name="tr", class_="papi_small_t")
        if Titrelist is None:
            continue

        for subBalise in Titrelist:
            if (subBalise != "\n"):
                for element in subBalise.contents:
                    titre.append(element)

        voisin = Titrelist.find_next_sibling()
        res[id_tournois] = []
        while isinstance(voisin, Tag) and isLine(voisin):
            grille = {}
            i = 0
            for element in voisin.contents:
                if (element != "\n"):
                    grille[titre[i]] = element.text
                    i += 1
            res[id_tournois].append(grille)
            voisin = voisin.find_next_sibling()
    includes.saveInJSON(res, "result")
def parsePerson():
    participants = {}
    personns = {}

    for fileIn in filesName:
        id_tournois = fileIn.split(".")[0]
        id_tournois = id_tournois.split("_")[1]

        titre = []
        fichierIn = open(directory + fileIn, mode="r", encoding="utf-8")
        soup = BeautifulSoup(fichierIn, 'html.parser')
        Titrelist = soup.table.find(name="tr", class_="papi_liste_t")
        person = {}

        if Titrelist is None:
            continue

        for subBalise in Titrelist:
            if (subBalise != "\n"):
                for element in subBalise.contents:
                    titre.append(element)
        dataPersonne = soup.table.findAll(name="tr", class_="papi_liste_f")
        i = 0
        for tr in dataPersonne:
            j = 0
            for element in tr.contents:
                if (element != "\n"):
                    person[titre[j]] = element.text
                    j += 1
            # print(person)
            personns[i] = person.copy()
            person.clear()
            i += 1
        dataPersonne = soup.table.findAll(name="tr", class_="papi_liste_c")
        for tr in dataPersonne:
            j = 0
            for td in tr.contents:
                if (td != "\n"):
                    person[titre[j]] = td.text
                    j += 1
            # print(person)
            personns[i] = person.copy()
            person.clear()
            i += 1
        participants[id_tournois] = personns.copy()
        personns.clear()

    includes.saveInJSON(participants, "participants")
def parseStats():
    files = os.listdir(includes.getDir(includes.stat))
    if len(files) == 0:
        print(
            "Il n'y a pas de fichiers dans le dossier 'webContent/stats'.\nVeuillez le peupler avec le script 'extractFromWeb'"
        )
        return

    stats = {}
    for filename in files:
        file = open(includes.getDir(includes.stat) + filename,
                    mode="r",
                    encoding="utf-8",
                    errors="replace")
        id = getId(filename)
        soup = BeautifulSoup(file, 'html.parser')

        table = soup.find("table", {"id": "TablePage"}).find("table")
        if table == None:
            continue
        flag_two_tr = False
        current_stat = {}
        for tr in table.find_all("tr", {"class": "papi_liste_t"}):
            category = getCategory(tr.find("td").text)
            voisin = tr.find_next_sibling()
            if flag_two_tr:
                flag_two_tr = False
                continue
            if isACategory(voisin):
                flag_two_tr = True
                voisin = voisin.find_next_sibling()
            current_stat[category] = {}
            while isinstance(voisin, Tag) and not isACategory(voisin):
                td_sous_cat = voisin.find("td", {"class": "papi_liste_c"})
                if td_sous_cat == None:
                    break
                td_value = td_sous_cat.find_next_sibling()
                sous_cat = td_sous_cat.text.split(" :")[0]
                value = td_value.text.split(" ")[0]
                current_stat[category][sous_cat] = value
                voisin = voisin.find_next_sibling()

        stats[id] = current_stat

    includes.saveInJSON(stats, "stats")
Exemple #5
0
def programme(annee, moisDeb=1, moisFin=12):
    TournoisDelAnnee = getTournoisAn(annee)
    tournoisDelAnneePeriode = getTournoisMois(TournoisDelAnnee, moisDeb,
                                              moisFin)
    classement_json = json.dumps(classement(tournoisDelAnneePeriode))
    includes.saveInJSON(classement_json, "classement")