pcs_live/pcslive.py

from bs4 import BeautifulSoup
import requests, time

class LiveStats:
    def __init__(self):
        self.refresh_live()
        self.get_races()

        self.timeline = []
        self.situation_long = []

    def refresh_live(self):
        req = requests.get("https://www.procyclingstats.com/")
        html = req.text
        soup = BeautifulSoup(html, "html.parser")

        all = soup.find_all(attrs={"class":"hp3-livestats"})
        live = all[0]
        for tag in live.find_all(attrs={"class":"inverse"}):
            tag.decompose()

        self.live = live
    
    def get_races(self):
        races_raw = self.live.find_all("li")
        self.races = []
        for race in races_raw:
            this_race = Race(race)
            self.races.append(this_race)

    def print_races(self):
        for race in self.races:
            race.print_stats()

class Race:
    def __init__(self, raw):
        self.raw = raw
        self.refresh_info()

    def refresh_info(self):
        title_r = self.raw.find(attrs={"class":"title"})
        status_r = self.raw.find(attrs={"class":"status"})
        togo_r = self.raw.find(attrs={"class":"togo"})
        situation_r = self.raw.find(attrs={"class":"situ_txt"})
        url_r = self.raw.find("a", href=True)

        self.title = self.remove_tags(title_r)
        self.status = self.remove_tags(status_r)
        self.togo = self.remove_tags(togo_r)
        self.situation = self.remove_tags(situation_r)
        self.url = self.remove_tags(url_r["href"])

    def print_stats(self):
        print(self.title)
        print(self.status)
        if self.togo != "None":
            print(self.togo, "to go")
            print(self.situation)
        print("===============")

    def print_raw(self):
        print(self.raw)
        print("")
        print(self.url)

    def get_race_page(self):
        if self.url != "None":
            full_url = "https://www.procyclingstats.com/" + self.url

            req = requests.get(full_url)
            html = req.text
            soup = BeautifulSoup(html, "html.parser")
            return soup
        return None

    def get_timeline(self):
        page = self.get_race_page()
        if page:
            all = page.find_all(attrs={"class":"timeline3cont"})
            live = all[0]
            timeline = live.find_all("li")
            self.timeline = []
            for item in timeline:
                stat = item.find(attrs={"class":"stat"})
                if stat:
                    stat_content = stat.find(attrs={"class":"textCont"})
                    self.timeline.append(self.remove_tags(stat_content))

    def get_situation_long(self):
        page = self.get_race_page()
        if page:
            all = page.find_all(attrs={"class":"situCont"})
            live = all[0]
            situation_long = live.find_all("li")
            self.situation_long = {}
            last_timegap = None
            for item in situation_long:
                #print(item)
                time_gap = item.find(attrs={"class":"time"})
                group_name = item.find(attrs={"class":"groupname"})
                rider = item.find(attrs={"class":"maxw200"})

                if time_gap:
                    tg = self.remove_tags(time_gap)
                    self.situation_long[tg] = []
                    last_timegap = tg
                rider_name = self.remove_tags(rider)
                if rider_name not in self.situation_long[last_timegap]:
                    self.situation_long[last_timegap].append(rider_name)

                #print(self.remove_tags(time_gap), self.remove_tags(group_name), self.remove_tags(riders))


    def remove_tags(self, text):
        text = str(text)
        text_soup = BeautifulSoup(text, "html.parser")
        for data in text_soup(["style", "script"]):
            data.decompose()
        return " ".join(text_soup.stripped_strings)