def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
data = {
"last_updated": convert_date(soup.find("tr").find("strong").text, "Stand: %d.%m.%Y, %H:%M Uhr"),
"data_source": data_source,
"lots": []
}
rows = soup.find_all("tr")
rows = rows[1:]
region_header = ""
for row in rows:
if len(row.find_all("th")) > 0:
# This is a header row, save it for later
region_header = row.find("th", {"class": "head1"}).text
else:
if row.find("td").text == "Gesamt":
continue
# This is a parking lot row
raw_lot_data = row.find_all("td")
if len(raw_lot_data) == 2:
type_and_name = process_name(raw_lot_data[0].text)
data["lots"].append({
"name": type_and_name[1],
"type": type_and_name[0],
"total": get_most_lots_from_known_data("Lübeck", type_and_name[1]),
"free": 0,
"region": region_header,
"state": process_state_map.get(raw_lot_data[1].text, ""),
"coords": geodata.coords(type_and_name[1]),
"id": generate_id(__file__, type_and_name[1]),
"forecast": False
})
elif len(raw_lot_data) == 4:
type_and_name = process_name(raw_lot_data[0].text)
data["lots"].append({
"name": type_and_name[1],
"type": type_and_name[0],
"total": int(raw_lot_data[1].text),
"free": int(raw_lot_data[2].text),
"region": region_header,
"state": "open",
"coords": geodata.coords(type_and_name[1]),
"id": generate_id(__file__, type_and_name[1]),
"forecast": False
})
return data
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
lot_table_trs = soup.select("table[cellpadding=5]")[0].find_all("tr")
data = {
"last_updated": convert_date(lot_table_trs[-1].text.strip(), "%d.%m.%Y %H:%M Uhr"),
"data_source": data_source,
"lots": []
}
for tr in lot_table_trs[1:-1]:
tds = tr.find_all("td")
type_and_name = process_name(tds[0].text)
data["lots"].append({
"name": type_and_name[1],
"type": type_and_name[0],
"free": int(tds[1].text),
"total": total_number_map.get(tds[0].text, 0),
"state": state_map.get(tds[2].text, ""),
"coords": geodata.coords(type_and_name[1]),
"id": generate_id(__file__, type_and_name[1]),
"forecast": False
})
return data
def parse_html(xml_data):
feed = feedparser.parse(xml_data)
last_updated = feed["entries"][0]["updated"]
data = {
"lots": [],
# remove trailing timezone for consensistency
"last_updated": last_updated.replace("Z", ""),
"data_source": data_source
}
for entry in feed["entries"]:
summary = parse_summary(entry["summary"])
title = parse_title(entry["title"])
old_id = entry["id"].split("=")[1]
data["lots"].append({
"name": title[0],
"address": title[1],
"id": generate_id(__file__, title[0]),
"state": summary[0],
"free": summary[1],
"total": total_number_map.get(title[0], 0),
"coords": geodata.coords(title[0]),
"forecast": False,
})
return data
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
free_lots = soup.find_all("td", {"class": "stell"})
assert len(free_lots) == 6, "Expect to find 6 lots in Bonn, got: %d" % len(
free_lots)
time = soup.find("td", {"class": "stand"}).text.strip()
lots = []
for idx, free in enumerate(free_lots):
lot = lot_map.get(idx)
lots.append({
"name": lot.name,
"coords": geodata.coords(lot.name),
"free": int(free.text),
"address": lot.address,
"total": lot.total,
"state": "nodata",
"id": generate_id(__file__, lot.name),
"forecast": False
})
return {
"last_updated": convert_date(time, "%d.%m.%y %H:%M:%S"),
"data_source": data_source,
"lots": lots
}
def parse_html(xml_data):
feed = feedparser.parse(xml_data)
last_updated = feed["entries"][0]["updated"]
data = {
"lots": [],
# remove trailing timezone for consensistency
"last_updated": last_updated.replace("Z", ""),
"data_source": data_source
}
for entry in feed["entries"]:
summary = parse_summary(entry["summary"])
title = parse_title(entry["title"])
old_id = entry["id"].split("=")[1]
data["lots"].append({
"name": title[0],
"address": title[1],
"id": generate_id(__file__, title[0]),
"state": summary[0],
"free": summary[1],
"total": total_number_map.get(title[0], 0),
"coords": geodata.coords(title[0]),
"forecast": False,
})
return data
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
data = {
"last_updated": convert_date(soup.p.string, "(%d.%m.%Y, %H.%M Uhr)"),
"data_source": data_source,
"lots": []
}
# get all lots
raw_lots = soup.find_all("tr")
for lot in raw_lots:
elements = lot.find_all("td")
lot_name = elements[0].text
data["lots"].append({
"name": lot_name,
"free": int(elements[1].text),
"total": data_map.get(lot_name)["total"],
"type": data_map.get(lot_name)["type"],
"address": data_map.get(lot_name)["address"],
"coords": geodata.coords(lot_name),
"state": "nodata",
"id": generate_id(__file__, lot_name),
"forecast": False
})
return data
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
free_lots = soup.find_all("td", {"class": "stell"})
assert len(free_lots) == 6, "Expect to find 6 lots in Bonn, got: %d" % len(free_lots)
time = soup.find("td", {"class": "stand"}).text.strip()
lots = []
for idx, free in enumerate(free_lots):
lot = lot_map.get(idx)
lots.append({
"name": lot.name,
"coords": geodata.coords(lot.name),
"free": int(free.text),
"address": lot.address,
"total": lot.total,
"state": "nodata",
"id": generate_id(__file__, lot.name),
"forecast": False
})
return {
"last_updated": convert_date(time, "%d.%m.%y %H:%M:%S"),
"data_source": data_source,
"lots": lots
}
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
data = {
"lots": [],
"data_source": data_source,
"last_updated": convert_date(soup.find(id="P1_LAST_UPDATE").text, "%d.%m.%Y %H:%M:%S")
}
for table in soup.find_all("table"):
if table["summary"] != "":
region = table["summary"]
for lot_row in table.find_all("tr"):
if lot_row.find("th") is not None:
continue
state_div = lot_row.find("div")
if "green" in state_div["class"]:
state = "open"
elif "yellow" in state_div["class"]:
state = "open"
elif "red" in state_div["class"]:
state = "open"
elif "park-closed" in state_div["class"]:
state = "closed"
else:
state = "nodata"
lot_name = lot_row.find("td", {"headers": "BEZEICHNUNG"}).text
try:
free = int(lot_row.find("td", {"headers": "FREI"}).text)
except ValueError:
free = 0
try:
total = int(lot_row.find("td", {"headers": "KAPAZITAET"}).text)
except ValueError:
total = get_most_lots_from_known_data("Dresden", lot_name)
id = generate_id(__file__, lot_name)
forecast = os.path.isfile("forecast_data/" + id + ".csv")
data["lots"].append({
"coords": geodata.coords(lot_name),
"name": lot_name,
"total": total,
"free": free,
"state": state,
"id": id,
"lot_type": type_map.get(lot_name, ""),
"address": address_map.get(lot_name, ""),
"forecast": forecast,
"region": region
})
return data
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
# last update time (UTC)
try:
update_time = convert_date(soup.select('p > strong')[-1].text, "Stand: %d.%m.%Y - %H:%M:%S")
except ValueError:
update_time = convert_date(soup.select('p > strong')[-2].text, "Stand: %d.%m.%Y - %H:%M:%S")
data = {
"last_updated": update_time,
"data_source": data_source,
"lots": []
}
# get all tables with lots
raw_lot_list = soup.find_all("div", {"class": "listing"})
# get all lots
for lot_list in raw_lot_list:
raw_lots = lot_list.select('tr + tr')
for lot in raw_lots:
lot_name = lot.select('a')[0].text
try:
lot_free = int(lot.select('td + td')[0].text)
lot_state = "open" if "green" in str(lot.select("td + td")[0]) else "closed"
except ValueError:
lot_free = 0
lot_state = "nodata"
data["lots"].append({
"name": lot_name,
"free": lot_free,
"total": total_number_map.get(lot_name, 0),
"coords": geodata.coords(lot_name),
"state": lot_state,
"id": generate_id(__file__, lot_name),
"forecast": False
})
return data
def parse_html(html):
# BeautifulSoup is a great and easy way to parse the html and find the bits and pieces we're looking for.
soup = BeautifulSoup(html)
# last_updated is the date when the data on the page was last updated, it should be listed on most pages
last_updated = soup.select("p#last_updated")[0].text
data = {
# convert_date is a utility function you can use to turn this date into the correct string format
"last_updated": convert_date(last_updated, "%d.%m.%Y %H:%M Uhr"),
"data_source": data_source,
"lots": []
}
for tr in soup.find_all("tr"):
lot_name = tr.find("td", {"class": "lot_name"}).text
lot_free = tr.find("td", {"class": "lot_free"}).text
lot_total = tr.find("td", {"class": "lot_total"}).text
lot_address = tr.find("td", {"class": "lot_address"}).text
lot_type = tr.find("td", {"class": "lot_type"}).text
# please be careful about the state only being allowed to contain either open, closed or nodata
# should the page list other states, please map these into the three listed possibilities
state = tr.find("td", {"class": "lot_state"}).text
data["lots"].append({
"name": lot_name,
"free": lot_free,
"total": lot_total,
"address": lot_address,
"coords": geodata.coords(lot_name),
"state": state,
"type": lot_type,
# use the utility function generate_id to generate an ID for this lot
# it takes this file path and the lot's name as params
"id": generate_id(__file__, lot_name),
"forecast": False,
})
return data
def parse_html(html):
# BeautifulSoup is a great and easy way to parse the html and find the bits and pieces we're looking for.
soup = BeautifulSoup(html)
# last_updated is the date when the data on the page was last updated, it should be listed on most pages
last_updated = soup.select("p#last_updated")[0].text
data = {
# convert_date is a utility function you can use to turn this date into the correct string format
"last_updated": convert_date(last_updated, "%d.%m.%Y %H:%M Uhr"),
"data_source": data_source,
"lots": []
}
for tr in soup.find_all("tr"):
lot_name = tr.find("td", {"class": "lot_name"}).text
lot_free = tr.find("td", {"class": "lot_free"}).text
lot_total = tr.find("td", {"class": "lot_total"}).text
lot_address = tr.find("td", {"class": "lot_address"}).text
lot_type = tr.find("td", {"class": "lot_type"}).text
# please be careful about the state only being allowed to contain either open, closed or nodata
# should the page list other states, please map these into the three listed possibilities
state = tr.find("td", {"class": "lot_state"}).text
data["lots"].append({
"name": lot_name,
"free": lot_free,
"total": lot_total,
"address": lot_address,
"coords": geodata.coords(lot_name),
"state": state,
"type": lot_type,
# use the utility function generate_id to generate an ID for this lot
# it takes this file path and the lot's name as params
"id": generate_id(__file__, lot_name),
"forecast": False,
})
return data
def parse_html(html):
# BeautifulSoup is a great and easy way to parse the html and find the bits and pieces we're looking for.
soup = BeautifulSoup(html, "html.parser")
# last_updated is the date when the data on the page was last updated
last_updated = str(soup.select("body"))
start = str.find(last_updated, "Letzte Aktualisierung:") + 23
last_updated = last_updated[start:start + 16] + ' Uhr'
data = {
# convert_date is a utility function you can use to turn this date into the correct string format
"last_updated": convert_date(last_updated, "%d.%m.%Y %H:%M Uhr"),
"data_source": data_source,
"lots": []
}
status_map = {
"Offen": "open",
"Geschlossen": "closed"
}
# Oldenburg does not send the totals on there website,
# so wie take some Values from a 2011st PDF:
# http://www.oldenburg.de/fileadmin/oldenburg/Benutzer/PDF/41/414/Parkplatz_Uebersicht2.pdf
# and http://gis4oldenburg.oldenburg.de/?es=C12S77
# what possible can go wrong ¯\_(ツ)_/¯
lots_map = {
"Waffenplatz": [650, "Waffenplatz 3"],
"City": [440, "Staulinie 10"],
"Galeria Kaufhof": [326, "Ritterstraße"],
"Pferdemarkt": [401, "Pferdemarkt 13"],
# CCO 1 & 2 are together only known together with 420, but they seem to be somewhat like this
"CCO Parkdeck 1": [190, "Heiligengeiststraße 4"],
"CCO Parkdeck 2": [230, "Heiligengeiststraße 4"],
"Hbf/ZOB": [358, "Karlstraße"],
"Theaterwall": [125, "Theaterwall 4"],
"Theatergarage": [107, "Roonstraße"],
"Heiligengeist-Höfe": [275, "Georgstraße"],
"Schlosshöfe": [430, "Mühlenstraße"],
}
for tr in soup.find_all("tr"):
if tr.td is None:
continue
td = tr.findAll('td')
lot_name = td[0].b.string
lot_free = int(td[1].b.text)
# get the values from the map above, or return zero
# should trown an execption -> [email protected]
lot_total = lots_map[lot_name][0]
lot_address = lots_map[lot_name][1]
# lot_type = tr.find("td").text
# please be careful about the state only being allowed to contain either open, closed or nodata
# should the page list other states, please map these into the three listed possibilities
state = status_map.get(td[3].text, "nodata")
data["lots"].append({
# use the utility function generate_id to generate an ID for this lot
# it takes this file path and the lot's name as params
"id": generate_id(__file__, lot_name),
"name": lot_name,
"free": lot_free,
"state": state,
"total": lot_total,
"address": lot_address,
"coords": geodata.coords(lot_name),
# "type": lot_type,
"forecast": False
})
return data
def parse_html(html):
soup = BeautifulSoup(html, "html.parser")
data = {
"lots": [],
"data_source":
data_source,
"last_updated":
convert_date(soup.find(id="P1_LAST_UPDATE").text, "%d.%m.%Y %H:%M:%S")
}
for table in soup.find_all("table"):
if table["summary"] != "":
region = table["summary"]
for lot_row in table.find_all("tr"):
if lot_row.find("th") is not None:
continue
state_div = lot_row.find("div")
if "green" in state_div["class"]:
state = "open"
elif "yellow" in state_div["class"]:
state = "open"
elif "red" in state_div["class"]:
state = "open"
elif "park-closed" in state_div["class"]:
state = "closed"
else:
state = "nodata"
lot_name = lot_row.find("td", {"headers": "BEZEICHNUNG"}).text
try:
free = int(lot_row.find("td", {"headers": "FREI"}).text)
except ValueError:
free = 0
try:
total = int(
lot_row.find("td", {
"headers": "KAPAZITAET"
}).text)
except ValueError:
total = get_most_lots_from_known_data("Dresden", lot_name)
id = generate_id(__file__, lot_name)
forecast = os.path.isfile("forecast_data/" + id + ".csv")
data["lots"].append({
"coords": geodata.coords(lot_name),
"name": lot_name,
"total": total,
"free": free,
"state": state,
"id": id,
"lot_type": type_map.get(lot_name, ""),
"address": address_map.get(lot_name, ""),
"forecast": forecast,
"region": region
})
return data
def parse_html(html):
# BeautifulSoup is a great and easy way to parse the html and find the bits and pieces we're looking for.
soup = BeautifulSoup(html, "html.parser")
# last_updated is the date when the data on the page was last updated
last_updated = str(soup.select("body"))
start = str.find(last_updated, "Letzte Aktualisierung:") + 23
last_updated = last_updated[start : start + 16] + " Uhr"
data = {
# convert_date is a utility function you can use to turn this date into the correct string format
"last_updated": convert_date(last_updated, "%d.%m.%Y %H:%M Uhr"),
"data_source": data_source,
"lots": [],
}
status_map = {"Offen": "open", "Geschlossen": "closed"}
# Oldenburg does not send the totals on there website,
# so wie take some Values from a 2011st PDF:
# http://www.oldenburg.de/fileadmin/oldenburg/Benutzer/PDF/41/414/Parkplatz_Uebersicht2.pdf
# and http://gis4oldenburg.oldenburg.de/?es=C12S77
# what possible can go wrong ¯\_(ツ)_/¯
lots_map = {
"Waffenplatz": [650, "Waffenplatz 3"],
"City": [440, "Staulinie 10"],
"Galeria Kaufhof": [326, "Ritterstraße"],
"Pferdemarkt": [401, "Pferdemarkt 13"],
# CCO 1 & 2 are together only known together with 420, but they seem to be somewhat like this
"CCO Parkdeck 1": [190, "Heiligengeiststraße 4"],
"CCO Parkdeck 2": [230, "Heiligengeiststraße 4"],
"Hbf/ZOB": [358, "Karlstraße"],
"Theaterwall": [125, "Theaterwall 4"],
"Theatergarage": [107, "Roonstraße"],
"Heiligengeist-Höfe": [275, "Georgstraße"],
"Schlosshöfe": [430, "Mühlenstraße"],
}
for tr in soup.find_all("tr"):
if tr.td is None:
continue
td = tr.findAll("td")
lot_name = td[0].b.string
lot_free = int(td[1].b.text)
# get the values from the map above, or return zero
# should trown an execption -> [email protected]
lot_total = lots_map[lot_name][0]
lot_address = lots_map[lot_name][1]
# lot_type = tr.find("td").text
# please be careful about the state only being allowed to contain either open, closed or nodata
# should the page list other states, please map these into the three listed possibilities
state = status_map.get(td[3].text, "nodata")
data["lots"].append(
{
# use the utility function generate_id to generate an ID for this lot
# it takes this file path and the lot's name as params
"id": generate_id(__file__, lot_name),
"name": lot_name,
"free": lot_free,
"state": state,
"total": lot_total,
"address": lot_address,
"coords": geodata.coords(lot_name),
# "type": lot_type,
"forecast": False,
}
)
return data