chainetv_web/backend/chainetv/emission.py

from bs4 import BeautifulSoup
import urllib.request
import re
from datetime import datetime, timedelta

#debug
#import pprint

class Emmission(object):

    def __init__(self):
        self._LoadreferencePage()

    def _LoadreferencePage(self):
        URL="https://www.programme-tv.net/programme/canal-5/"
        try:
            response = urllib.request.urlopen(URL)
        except urllib.error.URLError:
            return None
        print("load")
        self.html = BeautifulSoup(response.read(),"html.parser")
        self.timestamp=datetime.utcnow() 

    def parse_emmission(self,strsearch):
        if (self.timestamp > self.timestamp+timedelta(minutes=5)):
            self._LoadreferencePage()
        strsearch=strsearch.replace('É','E')
        linkchaine=self.html.find(text=re.compile(re.escape(strsearch)))
        if linkchaine == None:
            return "can't find channel"
        link = linkchaine.parent.parent.find_next_sibling().find("a")
        href = link['href']
        response = urllib.request.urlopen(href)
        parse=BeautifulSoup(response.read(),"html.parser")
        divcasting=parse.select_one(".descriptif")
        if (divcasting):
            casting=divcasting.find_all(href=re.compile("biographie"))
            count=0
            for actor in casting:
                casting[count]=actor.text
                count+=1
        else:
            casting= None
        divsynopsis=parse.select_one(".episode-synopsis")
        if (divsynopsis):
            img=divsynopsis.find_next('img')['data-src']
            synopsis=divsynopsis.select_one(".d-b").text
        else:
            img=None
            synopsis=""

        return {'title':link['title'],'href':href,'casting':casting,'synopsis':remove_first_space(synopsis),'img':img}


def remove_first_space (string):
    space_number=0
    for char in string:
        if char.isspace():
            space_number+=1
        else:
            break
    return string[space_number:]