from bs4 import BeautifulSoup import requests import datetime import pytz import workers.val from classes import * def getStation(name): return list(workers.val.validateName(name))[0] def connRequest(frm, to, count = 3, time = datetime.datetime.now(), mode = False, details = False, via = []): outdate = datetime.datetime.strftime(time,"%d.%m.%Y") outtime = datetime.datetime.strftime(time,"%H:%M") url = "http://fahrplan.oebb.at/bin/query.exe/dn?start=1&S=%s&Z=%s&REQ0JourneyDate=%s&time=%s&REQ0HafasNumCons0=%s%s" % (frm.extid if frm.extid else frm.name, to.extid if to.extid else to.name, outdate, outtime, count, "×el=arrive" if mode else "") for i in range(len(via)): url += "&REQ0JourneyStops%i.0G=%s&REQ0JourneyStops%i.0A=1" % (i + 1, via[i].extid if via[i].extid else via[i].name, i + 1) source = requests.get(url).text if "GO_conViewMode=outward" not in source: raise ValueError("No connection found.") juha = BeautifulSoup(source, "html5lib") if details: for a in juha.findAll("a"): if a.get("href") and "HWAI=CONNECTION$" in a.get("href"): dpage = a.get("href") ssource = requests.get(dpage).text suppe = BeautifulSoup(ssource, "html5lib") for i in range(0, count): cont = suppe.find("tr", id="trC0-%i" % i) if not cont: break # buyurl = None # # for url in cont.findAll("a"): # if url.get("href") and "https://tickets.oebb.at/de/ticket/ticket?" in url.get("href"): # buyurl = url.get("href") conn = Connection(details) for vst in via: conn.addVia(vst) lines = cont.findAll("tr", { "class": "tpDetails" })[1:] cdate = None for line in range(0, len(lines), 3): serv = lines[line:line + 3] dep = serv[0] arr = serv[1] det = serv[2] depst = list(workers.val.validateName(dep.find("td", { "class": "station" }).findAll("a")[0].string))[0] depdate = dep.find("td", { "class": "date" }).string.strip() or cdate deptime = dep.find("td", { "class": "timeValue" }).find("span").string.split()[1].strip() depprog = (dep.find("span", { "class": "prognosis" }).find("span") or dep.find("span", { "class": "prognosis" })).string.strip() or None depplat = (dep.find("td", { "class": "platform" }).find("span") or dep.find("td", { "class": "platform" })).string.strip() or None walk = dep.find("img", { "class": "product" }).get("src") == "/img/vs_oebb/fuss_pic.gif" name = dep.find("img", { "class": "product" }).get("alt") if not walk else "Walk" if not walk: purl = dep.find("td", { "class": "product" }).find("a").get("href") psource = requests.get(purl).text zuppa = BeautifulSoup(psource, "html5lib") dest = list(workers.val.validateName(zuppa.findAll("div", { "class": "block" })[2].text.split(":")[1].strip()))[0] arrst = list(workers.val.validateName(arr.find("td", { "class": "station" }).findAll("a")[0].string))[0] arrdate = (arr.find("td", { "class": "date" }).find("span") or arr.find("td", { "class": "date" })).string.strip() or depdate arrtime = arr.find("td", { "class": "timeValue" }).find("span").string.split()[1].strip() arrprog = (arr.find("span", { "class": "prognosis" }).find("span") or arr.find("span", { "class": "prognosis" })).string.strip() or None arrplat = (arr.find("td", { "class": "platform" }).find("span") or arr.find("td", { "class": "platform" })).string.strip() or None depts = datetime.datetime.strptime("%s %s" % (depdate, deptime), "%d.%m.%Y %H:%M") arrts = datetime.datetime.strptime("%s %s" % (arrdate, arrtime), "%d.%m.%Y %H:%M") depprog = deptime if depprog == "pünktlich" else depprog arrprog = arrtime if arrprog == "pünktlich" else arrprog cdate = arrdate svc = Service(name, depst, depts, arrst, arrts, dest, depplat, depprog, arrplat, arrprog) conn.addService(svc) yield conn else: for i in range(0, count): det = juha.find("tr", id="trOverviewC0-%i" % i) if not det: break stations = det.find("td", { "class": "station" }).findAll("div") depst = getStation(stations[0].text.strip()) arrst = getStation(stations[-1].text.strip()) dates = list(det.find("td", { "class": "date" }).strings) depdate = dates[0] try: arrdate = dates[1] except: arrdate = depdate times = det.find("div", { "class": "planed" }).text deptime = times.split()[0] arrtime = times.split()[2] projections = det.find("div", { "class": "prognosis" }) curdep = None curarr = None depts = datetime.datetime.strptime("%s %s" % (depdate, deptime), "%d.%m.%Y %H:%M") arrts = datetime.datetime.strptime("%s %s" % (arrdate, arrtime), "%d.%m.%Y %H:%M") name = "/".join([img.get("title") for img in det.findAll("img", { "class": "product" })]) # ticketurl = det.find("td", { "class": "fares" }).find("a").get("href") svc = Service(name, depst, depts, arrst, arrts, currdep = curdep, curarr = curarr) conn = Connection(details) for vst in via: conn.addVia(vst) conn.addService(svc) yield conn def worker(frm, to, count = 3, time = datetime.datetime.now(pytz.timezone("Europe/Vienna")), mode = False, details = False, json = False, via = None): conns = list(connRequest(getStation(frm), getStation(to), count, time, mode, details, [getStation(vst) for vst in via] if via else [])) output = """ """ if not json else """{ \"connections\": [ """ for i in range(len(conns)): output += (conns[i].xml(1, i) + "\n") if not json else (conns[i].json(2, i) + ("\n" if i == len(conns) - 1 else ",\n")) output += "" if not json else " ]\n}" return output