def _get_log_counts_from_print_page(soup):
"""Return a dictionary of all log counts found in the page
representation, based on the print page.
:param bs4.BeautifulSoup soup: Parsed html document of the cache print page.
"""
# The print page does not use any IDs, so we use some more complicated approach here and
# search for the paragraph containing the log type images.
p_meta = soup.find_all("p", "Meta")
element = None
for entry in p_meta:
if "images/logtypes" in str(entry):
element = entry
break
if not element:
raise errors.ValueError("Log counts could not be found.")
# Text gives numbers and verbose descriptions of the current values as well as an
# introductory text. So we have to perform number checks for each element and only keep
# the numbers.
# The values might contain thousand separators, which we have to remove before converting
# them to real numbers.
words = element.text.split()
values = []
for word in words:
word = word.replace(",", "").replace(".", "")
if word and word.isdigit():
values.append(int(word))
# Retrieve the list of image sources.
images = element.find_all("img")
types = []
for image in images:
type = image["src"] # "../images/logtypes/2.png"
type = type.split("/")[-1].split(".")[0] # "2"
type = LogType.from_filename(type)
types.append(type)
# Prevent possible wrong assignments when the list sizes differ for some unknown reason.
if not len(values) == len(types):
raise errors.ValueError(
"Different list sizes getting log counts: {} types and {} counts."
.format(len(types), len(values)))
# Finally create the mapping.
log_counts = dict(zip(types, values))
return log_counts
def test_from_filename(self):
with self.subTest("valid types"):
self.assertEqual(Type.found_it, Type.from_filename("2"))
self.assertEqual(Type.visit, Type.from_filename("75"))
with self.subTest("special valid types"):
self.assertEqual(Type.visit, Type.from_filename("1001"))
self.assertEqual(Type.publish_listing, Type.from_filename("1003"))
with self.subTest("invalid type"):
with self.assertRaises(PycachingValueError):
Type.from_filename("6666")
def test_from_filename(self):
with self.subTest("valid types"):
self.assertEqual(Type.found_it, Type.from_filename("2"))
self.assertEqual(Type.visit, Type.from_filename("75"))
with self.subTest("special valid types"):
self.assertEqual(Type.visit, Type.from_filename("1001"))
self.assertEqual(Type.publish_listing, Type.from_filename("1003"))
with self.subTest("invalid type"):
with self.assertRaises(PycachingValueError):
Type.from_filename("6666")
def load_logbook(self, limit=float("inf")):
"""Return a generator of logs for this cache.
Yield instances of :class:`.Log` filled with log data.
:param int limit: Maximum number of logs to generate.
"""
logging.info("Loading logbook for {}...".format(self))
page = 0
per_page = min(limit,
100) # max number to fetch in one request is 100 items
while True:
# get one page
logbook_page = self._logbook_get_page(page, per_page)
page += 1
if not logbook_page:
# result is empty - no more logs
return
for log_data in logbook_page:
limit -= 1 # handle limit
if limit < 0:
return
img_filename = log_data["LogTypeImage"].rsplit(
".", 1)[0] # filename w/o extension
# create and fill log object
l = Log()
l.type = LogType.from_filename(img_filename)
l.text = log_data["LogText"]
l.visited = log_data["Visited"]
l.author = log_data["UserName"]
yield l
def _get_log_counts_from_cache_details(soup):
"""Return a dictionary of all log counts found in the page
representation, based on the cache details page.
:param bs4.BeautifulSoup soup: Parsed html document of the cache details page.
"""
lbl_find_counts = soup.find("span",
{"id": "ctl00_ContentBody_lblFindCounts"})
log_totals = lbl_find_counts.find("p", "LogTotals")
# Text gives numbers separated by a lot of spaces, splitting retrieves the numbers.
# The values might contain thousand separators, which we have to remove before converting
# them to real numbers.
values = log_totals.text.split()
values = [
int(value.replace(",", "").replace(".", "")) for value in values
]
# Retrieve the list of image sources.
images = log_totals.find_all("img")
types = []
for image in images:
type = image["src"] # "../images/logtypes/2.png"
type = type.split("/")[-1].split(".")[0] # "2"
type = LogType.from_filename(type)
types.append(type)
# Prevent possible wrong assignments when the list sizes differ for some unknown reason.
if not len(values) == len(types):
raise errors.ValueError(
"Different list sizes getting log counts: {} types and {} counts."
.format(len(types), len(values)))
# Finally create the mapping.
log_counts = dict(zip(types, values))
return log_counts
def load_logbook(self, limit=float("inf")):
"""Return a generator of logs for this cache.
Yield instances of :class:`.Log` filled with log data.
:param int limit: Maximum number of logs to generate.
"""
logging.info("Loading logbook for {}...".format(self))
page = 0
per_page = min(limit, 100) # max number to fetch in one request is 100 items
while True:
# get one page
logbook_page = self._logbook_get_page(page, per_page)
page += 1
if not logbook_page:
# result is empty - no more logs
return
for log_data in logbook_page:
limit -= 1 # handle limit
if limit < 0:
return
img_filename = log_data["LogTypeImage"].rsplit(".", 1)[0] # filename w/o extension
# create and fill log object
l = Log()
l.type = LogType.from_filename(img_filename)
l.text = log_data["LogText"]
l.visited = log_data["Visited"]
l.author = log_data["UserName"]
yield l
def load(self):
"""Load all possible cache details.
Use full cache details page. Therefore all possible properties are filled in, but the
loading is a bit slow.
If you want to load basic details about a PM only cache, the :class:`.PMOnlyException` is
still thrown, but avaliable details are filled in. If you know, that the cache you are
loading is PM only, please consider using :meth:`load_quick` as it will load the same
details, but quicker.
.. note::
This method is called automatically when you access a property which isn't yet filled in
(so-called "lazy loading"). You don't have to call it explicitly.
:raise .PMOnlyException: If cache is PM only and current user is basic member.
:raise .LoadError: If cache loading fails (probably because of not existing cache).
"""
try:
# pick url based on what info we have right now
if hasattr(self, "url"):
root = self.geocaching._request(self.url)
elif hasattr(self, "_wp"):
root = self.geocaching._request(self._urls["cache_details"],
params={"wp": self._wp})
else:
raise errors.LoadError("Cache lacks info for loading")
except errors.Error as e:
# probably 404 during cache loading - cache not exists
raise errors.LoadError("Error in loading cache") from e
# check for PM only caches if using free account
self.pm_only = root.find("section", "pmo-banner") is not None
cache_details = root.find(
id="ctl00_divContentMain") if self.pm_only else root.find(
id="cacheDetails")
# details also avaliable for basic members for PM only caches -----------------------------
if self.pm_only:
self.wp = cache_details.find("li", "li__gccode").text.strip()
self.name = cache_details.find("h1").text.strip()
type = cache_details.find("img").get(
"src") # "/play/Content/images/cache-types/3.png"
type = type.split("/")[-1].rsplit(".", 1)[0] # "3"
self.type = Type.from_filename(type)
author = cache_details.find(id="ctl00_ContentBody_uxCacheBy").text
self.author = author[len("A cache by "):]
# parse cache detail list into a python list
details = cache_details.find("ul",
"ul__hide-details").text.split("\n")
self.difficulty = float(details[2])
self.terrain = float(details[5])
self.size = Size.from_string(details[8])
self.favorites = int(details[11])
else:
# parse from <title> - get first word
try:
self.wp = root.title.string.split(" ")[0]
except:
raise errors.LoadError()
self.name = cache_details.find("h2").text
type = cache_details.select_one("svg.cache-icon use").get(
"xlink:href") # "cache-types.svg#icon-3-disabled"
type = type.split("#")[-1].replace("_", "-").split("-")[1] # "3"
self.type = Type.from_filename(type)
self.author = cache_details("a")[1].text
D_and_T_img = root.find("div", "CacheStarLabels").find_all("img")
self.difficulty, self.terrain = [
float(img.get("alt").split()[0]) for img in D_and_T_img
]
size = root.find("div", "CacheSize")
size = size.find("img").get("src") # size img src
size = size.split("/")[-1].rsplit(".",
1)[0] # filename w/o extension
self.size = Size.from_filename(size)
if self.pm_only:
raise errors.PMOnlyException()
# details not avaliable for basic members for PM only caches ------------------------------
pm_only_warning = root.find("p", "Warning NoBottomSpacing")
self.pm_only = pm_only_warning and ("Premium Member Only"
in pm_only_warning.text) or False
attributes_widget, inventory_widget, *_ = root.find_all(
"div", "CacheDetailNavigationWidget")
hidden = cache_details.find(
"div", "minorCacheDetails").find_all("div")[1].text
self.hidden = parse_date(hidden.split(":")[-1])
self.location = Point.from_string(root.find(id="uxLatLon").text)
self.state = root.find("ul", "OldWarning") is None
log_image = root.find(id="ctl00_ContentBody_GeoNav_logTypeImage")
if log_image:
log_image_filename = log_image.get("src").split("/")[-1].rsplit(
".", 1)[0] # filename w/o extension
self._found_status = Log(
type=LogType.from_filename(log_image_filename))
else:
self._found_status = None
attributes_raw = attributes_widget.find_all("img")
attributes_raw = [
_.get("src").split("/")[-1].rsplit("-", 1) for _ in attributes_raw
]
self.attributes = {
attribute_name: appendix.startswith("yes")
for attribute_name, appendix in attributes_raw
if not appendix.startswith("blank")
}
self.summary = root.find(id="ctl00_ContentBody_ShortDescription").text
self.description = root.find(
id="ctl00_ContentBody_LongDescription").text
self.hint = rot13(root.find(id="div_hint").text.strip())
favorites = root.find("span", "favorite-value")
if favorites:
self.favorites = int(favorites.text)
else:
self.favorites = 0
js_content = "\n".join(map(lambda i: i.text, root.find_all("script")))
self._logbook_token = re.findall("userToken\\s*=\\s*'([^']+)'",
js_content)[0]
# find original location if any
if "oldLatLng\":" in js_content:
old_lat_long = js_content.split("oldLatLng\":")[1].split(
']')[0].split('[')[1]
self.original_location = Point(old_lat_long)
else:
self.original_location = None
# if there are some trackables
if len(inventory_widget.find_all("a")) >= 3:
trackable_page_url = inventory_widget.find(
id="ctl00_ContentBody_uxTravelBugList_uxViewAllTrackableItems")
self._trackable_page_url = trackable_page_url.get("href")[
3:] # has "../" on start
else:
self._trackable_page_url = None
# Additional Waypoints
self.waypoints = Waypoint.from_html(root,
"ctl00_ContentBody_Waypoints")
logging.debug("Cache loaded: {}".format(self))
def load(self):
"""Load all possible cache details.
Use full cache details page. Therefore all possible properties are filled in, but the
loading is a bit slow.
If you want to load basic details about a PM only cache, the :class:`.PMOnlyException` is
still thrown, but avaliable details are filled in. If you know, that the cache you are
loading is PM only, please consider using :meth:`load_quick` as it will load the same
details, but quicker.
.. note::
This method is called automatically when you access a property which isn't yet filled in
(so-called "lazy loading"). You don't have to call it explicitly.
:raise .PMOnlyException: If cache is PM only and current user is basic member.
:raise .LoadError: If cache loading fails (probably because of not existing cache).
"""
try:
# pick url based on what info we have right now
if hasattr(self, "url"):
root = self.geocaching._request(self.url)
elif hasattr(self, "_wp"):
root = self.geocaching._request(self._urls["cache_details"],
params={"wp": self._wp})
else:
raise errors.LoadError("Cache lacks info for loading")
except errors.Error as e:
# probably 404 during cache loading - cache not exists
raise errors.LoadError("Error in loading cache") from e
# check for PM only caches if using free account
self.pm_only = root.find("section", "pmo-banner") is not None
cache_details = root.find(id="ctl00_divContentMain") if self.pm_only else root.find(id="cacheDetails")
# details also avaliable for basic members for PM only caches -----------------------------
if self.pm_only:
self.wp = cache_details.find("li", "li__gccode").text.strip()
self.name = cache_details.find("h1").text.strip()
type = cache_details.find("img").get("src") # "/play/Content/images/cache-types/3.png"
type = type.split("/")[-1].rsplit(".", 1)[0] # "3"
self.type = Type.from_filename(type)
author = cache_details.find(id="ctl00_ContentBody_uxCacheBy").text
self.author = author[len("A cache by "):]
# parse cache detail list into a python list
details = cache_details.find("ul", "ul__hide-details").text.split("\n")
self.difficulty = float(details[2])
self.terrain = float(details[5])
self.size = Size.from_string(details[8])
self.favorites = int(details[11])
else:
# parse from <title> - get first word
try:
self.wp = root.title.string.split(" ")[0]
except:
raise errors.LoadError()
self.name = cache_details.find("h2").text
type = cache_details.select_one("svg.cache-icon use").get("xlink:href") # "cache-types.svg#icon-3-disabled"
type = type.split("#")[-1].replace("_", "-").split("-")[1] # "3"
self.type = Type.from_filename(type)
self.author = cache_details("a")[1].text
D_and_T_img = root.find("div", "CacheStarLabels").find_all("img")
self.difficulty, self.terrain = [float(img.get("alt").split()[0]) for img in D_and_T_img]
size = root.find("div", "CacheSize")
size = size.find("img").get("src") # size img src
size = size.split("/")[-1].rsplit(".", 1)[0] # filename w/o extension
self.size = Size.from_filename(size)
if self.pm_only:
raise errors.PMOnlyException()
# details not avaliable for basic members for PM only caches ------------------------------
pm_only_warning = root.find("p", "Warning NoBottomSpacing")
self.pm_only = pm_only_warning and ("Premium Member Only" in pm_only_warning.text) or False
attributes_widget, inventory_widget, *_ = root.find_all("div", "CacheDetailNavigationWidget")
hidden = cache_details.find("div", "minorCacheDetails").find_all("div")[1].text
self.hidden = parse_date(hidden.split(":")[-1])
self.location = Point.from_string(root.find(id="uxLatLon").text)
self.state = root.find("ul", "OldWarning") is None
log_image = root.find(id="ctl00_ContentBody_GeoNav_logTypeImage")
if log_image:
log_image_filename = log_image.get("src").split("/")[-1].rsplit(".", 1)[0] # filename w/o extension
self._found_status = Log(type=LogType.from_filename(log_image_filename))
else:
self._found_status = None
attributes_raw = attributes_widget.find_all("img")
attributes_raw = [_.get("src").split("/")[-1].rsplit("-", 1) for _ in attributes_raw]
self.attributes = {attribute_name: appendix.startswith("yes") for attribute_name, appendix
in attributes_raw if not appendix.startswith("blank")}
self.summary = root.find(id="ctl00_ContentBody_ShortDescription").text
self.description = root.find(id="ctl00_ContentBody_LongDescription").text
self.hint = rot13(root.find(id="div_hint").text.strip())
favorites = root.find("span", "favorite-value")
if favorites:
self.favorites = int(favorites.text)
else:
self.favorites = 0
js_content = "\n".join(map(lambda i: i.text, root.find_all("script")))
self._logbook_token = re.findall("userToken\\s*=\\s*'([^']+)'", js_content)[0]
# find original location if any
if "oldLatLng\":" in js_content:
old_lat_long = js_content.split("oldLatLng\":")[1].split(']')[0].split('[')[1]
self.original_location = Point(old_lat_long)
else:
self.original_location = None
# if there are some trackables
if len(inventory_widget.find_all("a")) >= 3:
trackable_page_url = inventory_widget.find(id="ctl00_ContentBody_uxTravelBugList_uxViewAllTrackableItems")
self._trackable_page_url = trackable_page_url.get("href")[3:] # has "../" on start
else:
self._trackable_page_url = None
# Additional Waypoints
self.waypoints = Waypoint.from_html(root, "ctl00_ContentBody_Waypoints")
logging.debug("Cache loaded: {}".format(self))