Mirrors/kleinanzeigen-bot
1
0
Fork 0
mirror of https://github.com/Second-Hand-Friends/kleinanzeigen-bot.git synced 2026-03-12 10:31:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

refact: apply consistent formatting

Browse Source
This commit is contained in:
sebthom
2025-04-27 23:54:22 +02:00
parent fe33a0e461
commit ef923a8337
21 changed files with 1020 additions and 709 deletions
Download Patch File Download Diff File Expand all files Collapse all files

252
src/kleinanzeigen_bot/extract.py
View File

@@ -36,22 +36,22 @@ class AdExtractor(WebScrapingMixin):
"""
# create sub-directory for ad(s) to download (if necessary):
relative_directory = 'downloaded-ads'
relative_directory = "downloaded-ads"
# make sure configured base directory exists
if not os.path.exists(relative_directory) or not os.path.isdir(relative_directory):
os.mkdir(relative_directory)
LOG.info('Created ads directory at ./%s.', relative_directory)
LOG.info("Created ads directory at ./%s.", relative_directory)
new_base_dir = os.path.join(relative_directory, f'ad_{ad_id}')
if os.path.exists(new_base_dir):
LOG.info('Deleting current folder of ad %s...', ad_id)
LOG.info("Deleting current folder of ad %s...", ad_id)
shutil.rmtree(new_base_dir)
os.mkdir(new_base_dir)
LOG.info('New directory for ad created at %s.', new_base_dir)
LOG.info("New directory for ad created at %s.", new_base_dir)
# call extraction function
info = await self._extract_ad_page_info(new_base_dir, ad_id)
ad_file_path = new_base_dir + '/' + f'ad_{ad_id}.yaml'
ad_file_path = new_base_dir + "/" + f'ad_{ad_id}.yaml'
dicts.save_dict(ad_file_path, info)
async def _download_images_from_ad_page(self, directory:str, ad_id:int) -> list[str]:
@@ -67,18 +67,18 @@ class AdExtractor(WebScrapingMixin):
img_paths = []
try:
# download all images from box
image_box = await self.web_find(By.CLASS_NAME, 'galleryimage-large')
image_box = await self.web_find(By.CLASS_NAME, "galleryimage-large")
n_images = len(await self.web_find_all(By.CSS_SELECTOR, '.galleryimage-element[data-ix]', parent = image_box))
LOG.info('Found %s.', i18n.pluralize("image", n_images))
n_images = len(await self.web_find_all(By.CSS_SELECTOR, ".galleryimage-element[data-ix]", parent = image_box))
LOG.info("Found %s.", i18n.pluralize("image", n_images))
img_element:Element = await self.web_find(By.CSS_SELECTOR, 'div:nth-child(1) > img', parent = image_box)
img_fn_prefix = 'ad_' + str(ad_id) + '__img'
img_element:Element = await self.web_find(By.CSS_SELECTOR, "div:nth-child(1) > img", parent = image_box)
img_fn_prefix = "ad_" + str(ad_id) + "__img"
img_nr = 1
dl_counter = 0
while img_nr <= n_images: # scrolling + downloading
current_img_url = img_element.attrs['src'] # URL of the image
current_img_url = img_element.attrs["src"] # URL of the image
if current_img_url is None:
continue
@@ -86,43 +86,43 @@ class AdExtractor(WebScrapingMixin):
content_type = response.info().get_content_type()
file_ending = mimetypes.guess_extension(content_type)
img_path = f"{directory}/{img_fn_prefix}{img_nr}{file_ending}"
with open(img_path, 'wb') as f:
with open(img_path, "wb") as f:
shutil.copyfileobj(response, f)
dl_counter += 1
img_paths.append(img_path.rsplit('/', maxsplit = 1)[-1])
img_paths.append(img_path.rsplit("/", maxsplit = 1)[-1])
# navigate to next image (if exists)
if img_nr < n_images:
try:
# click next button, wait, and re-establish reference
await (await self.web_find(By.CLASS_NAME, 'galleryimage--navigation--next')).click()
await (await self.web_find(By.CLASS_NAME, "galleryimage--navigation--next")).click()
new_div = await self.web_find(By.CSS_SELECTOR, f'div.galleryimage-element:nth-child({img_nr + 1})')
img_element = await self.web_find(By.TAG_NAME, 'img', parent = new_div)
img_element = await self.web_find(By.TAG_NAME, "img", parent = new_div)
except TimeoutError:
LOG.error('NEXT button in image gallery somehow missing, aborting image fetching.')
LOG.error("NEXT button in image gallery somehow missing, aborting image fetching.")
break
img_nr += 1
LOG.info('Downloaded %s.', i18n.pluralize("image", dl_counter))
LOG.info("Downloaded %s.", i18n.pluralize("image", dl_counter))
except TimeoutError: # some ads do not require images
LOG.warning('No image area found. Continuing without downloading images.')
LOG.warning("No image area found. Continuing without downloading images.")
return img_paths
def extract_ad_id_from_ad_url(self, url: str) -> int:
def extract_ad_id_from_ad_url(self, url:str) -> int:
"""
Extracts the ID of an ad, given by its reference link.
:param url: the URL to the ad page
:return: the ad ID, a (ten-digit) integer number
"""
num_part = url.split('/')[-1] # suffix
id_part = num_part.split('-')[0]
num_part = url.split("/")[-1] # suffix
id_part = num_part.split("-")[0]
try:
path = url.split('?', 1)[0] # Remove query string if present
last_segment = path.rstrip('/').split('/')[-1] # Get last path component
id_part = last_segment.split('-')[0] # Extract part before first hyphen
path = url.split("?", 1)[0] # Remove query string if present
last_segment = path.rstrip("/").split("/")[-1] # Get last path component
id_part = last_segment.split("-")[0] # Extract part before first hyphen
return int(id_part)
except (IndexError, ValueError) as ex:
LOG.warning("Failed to extract ad ID from URL '%s': %s", url, ex)
@@ -135,41 +135,41 @@ class AdExtractor(WebScrapingMixin):
:return: the links to your ad pages
"""
# navigate to "your ads" page
await self.web_open('https://www.kleinanzeigen.de/m-meine-anzeigen.html')
await self.web_open("https://www.kleinanzeigen.de/m-meine-anzeigen.html")
await self.web_sleep(2000, 3000) # Consider replacing with explicit waits later
# Try to find the main ad list container first
try:
ad_list_container = await self.web_find(By.ID, 'my-manageitems-adlist')
ad_list_container = await self.web_find(By.ID, "my-manageitems-adlist")
except TimeoutError:
LOG.warning('Ad list container #my-manageitems-adlist not found. Maybe no ads present?')
LOG.warning("Ad list container #my-manageitems-adlist not found. Maybe no ads present?")
return []
# --- Pagination handling ---
multi_page = False
try:
# Correct selector: Use uppercase '.Pagination'
pagination_section = await self.web_find(By.CSS_SELECTOR, '.Pagination', timeout=10) # Increased timeout slightly
pagination_section = await self.web_find(By.CSS_SELECTOR, ".Pagination", timeout = 10) # Increased timeout slightly
# Correct selector: Use 'aria-label'
# Also check if the button is actually present AND potentially enabled (though enabled check isn't strictly necessary here, only for clicking later)
next_buttons = await self.web_find_all(By.CSS_SELECTOR, 'button[aria-label="Nächste"]', parent=pagination_section)
next_buttons = await self.web_find_all(By.CSS_SELECTOR, 'button[aria-label="Nächste"]', parent = pagination_section)
if next_buttons:
# Check if at least one 'Nächste' button is not disabled (optional but good practice)
enabled_next_buttons = [btn for btn in next_buttons if not btn.attrs.get('disabled')]
enabled_next_buttons = [btn for btn in next_buttons if not btn.attrs.get("disabled")]
if enabled_next_buttons:
multi_page = True
LOG.info('Multiple ad pages detected.')
LOG.info("Multiple ad pages detected.")
else:
LOG.info('Next button found but is disabled. Assuming single effective page.')
LOG.info("Next button found but is disabled. Assuming single effective page.")
else:
LOG.info('No "Naechste" button found within pagination. Assuming single page.')
except TimeoutError:
# This will now correctly trigger only if the '.Pagination' div itself is not found
LOG.info('No pagination controls found. Assuming single page.')
LOG.info("No pagination controls found. Assuming single page.")
except Exception as e:
LOG.exception("Error during pagination detection: %s", e)
LOG.info('Assuming single page due to error during pagination check.')
LOG.info("Assuming single page due to error during pagination check.")
# --- End Pagination Handling ---
refs:list[str] = []
@@ -182,8 +182,8 @@ class AdExtractor(WebScrapingMixin):
# Re-find the ad list container on the current page/state
try:
ad_list_container = await self.web_find(By.ID, 'my-manageitems-adlist')
list_items = await self.web_find_all(By.CLASS_NAME, 'cardbox', parent=ad_list_container)
ad_list_container = await self.web_find(By.ID, "my-manageitems-adlist")
list_items = await self.web_find_all(By.CLASS_NAME, "cardbox", parent = ad_list_container)
LOG.info("Found %s ad items on page %s.", len(list_items), current_page)
except TimeoutError:
LOG.warning("Could not find ad list container or items on page %s.", current_page)
@@ -192,7 +192,7 @@ class AdExtractor(WebScrapingMixin):
# Extract references using the CORRECTED selector
try:
page_refs = [
(await self.web_find(By.CSS_SELECTOR, 'div.manageitems-item-ad h3 a.text-onSurface', parent=li)).attrs['href']
(await self.web_find(By.CSS_SELECTOR, "div.manageitems-item-ad h3 a.text-onSurface", parent = li)).attrs["href"]
for li in list_items
]
refs.extend(page_refs)
@@ -207,12 +207,12 @@ class AdExtractor(WebScrapingMixin):
# --- Navigate to next page ---
try:
# Find the pagination section again (scope might have changed after scroll/wait)
pagination_section = await self.web_find(By.CSS_SELECTOR, '.Pagination', timeout=5)
pagination_section = await self.web_find(By.CSS_SELECTOR, ".Pagination", timeout = 5)
# Find the "Next" button using the correct aria-label selector and ensure it's not disabled
next_button_element = None
possible_next_buttons = await self.web_find_all(By.CSS_SELECTOR, 'button[aria-label="Nächste"]', parent=pagination_section)
possible_next_buttons = await self.web_find_all(By.CSS_SELECTOR, 'button[aria-label="Nächste"]', parent = pagination_section)
for btn in possible_next_buttons:
if not btn.attrs.get('disabled'): # Check if the button is enabled
if not btn.attrs.get("disabled"): # Check if the button is enabled
next_button_element = btn
break # Found an enabled next button
@@ -235,7 +235,7 @@ class AdExtractor(WebScrapingMixin):
# --- End Navigation ---
if not refs:
LOG.warning('No ad URLs were extracted.')
LOG.warning("No ad URLs were extracted.")
return refs
@@ -246,27 +246,27 @@ class AdExtractor(WebScrapingMixin):
"""
if reflect.is_integer(id_or_url):
# navigate to start page, otherwise page can be None!
await self.web_open('https://www.kleinanzeigen.de/')
await self.web_open("https://www.kleinanzeigen.de/")
# enter the ad ID into the search bar
await self.web_input(By.ID, "site-search-query", id_or_url)
# navigate to ad page and wait
await self.web_check(By.ID, 'site-search-submit', Is.CLICKABLE)
submit_button = await self.web_find(By.ID, 'site-search-submit')
await self.web_check(By.ID, "site-search-submit", Is.CLICKABLE)
submit_button = await self.web_find(By.ID, "site-search-submit")
await submit_button.click()
else:
await self.web_open(str(id_or_url)) # navigate to URL directly given
await self.web_sleep()
# handle the case that invalid ad ID given
if self.page.url.endswith('k0'):
LOG.error('There is no ad under the given ID.')
if self.page.url.endswith("k0"):
LOG.error("There is no ad under the given ID.")
return False
# close (warning) popup, if given
try:
await self.web_find(By.ID, 'vap-ovrly-secure')
LOG.warning('A popup appeared!')
await self.web_click(By.CLASS_NAME, 'mfp-close')
await self.web_find(By.ID, "vap-ovrly-secure")
LOG.warning("A popup appeared!")
await self.web_click(By.CLASS_NAME, "mfp-close")
await self.web_sleep()
except TimeoutError:
pass
@@ -280,22 +280,22 @@ class AdExtractor(WebScrapingMixin):
:param ad_id: the ad ID, already extracted by a calling function
:return: a dictionary with the keys as given in an ad YAML, and their respective values
"""
info:dict[str, Any] = {'active': True}
info:dict[str, Any] = {"active": True}
# extract basic info
info['type'] = 'OFFER' if 's-anzeige' in self.page.url else 'WANTED'
title:str = await self.web_text(By.ID, 'viewad-title')
info["type"] = "OFFER" if "s-anzeige" in self.page.url else "WANTED"
title:str = await self.web_text(By.ID, "viewad-title")
LOG.info('Extracting information from ad with title "%s"', title)
info['category'] = await self._extract_category_from_ad_page()
info['title'] = title
info["category"] = await self._extract_category_from_ad_page()
info["title"] = title
# Get raw description text
raw_description = (await self.web_text(By.ID, 'viewad-description-text')).strip()
raw_description = (await self.web_text(By.ID, "viewad-description-text")).strip()
# Get prefix and suffix from config
prefix = get_description_affixes(self.config, prefix=True)
suffix = get_description_affixes(self.config, prefix=False)
prefix = get_description_affixes(self.config, prefix = True)
suffix = get_description_affixes(self.config, prefix = False)
# Remove prefix and suffix if present
description_text = raw_description
@@ -304,38 +304,38 @@ class AdExtractor(WebScrapingMixin):
if suffix and description_text.endswith(suffix.strip()):
description_text = description_text[:-len(suffix.strip())]
info['description'] = description_text.strip()
info["description"] = description_text.strip()
info['special_attributes'] = await self._extract_special_attributes_from_ad_page()
if "art_s" in info['special_attributes']:
info["special_attributes"] = await self._extract_special_attributes_from_ad_page()
if "art_s" in info["special_attributes"]:
# change e.g. category "161/172" to "161/172/lautsprecher_kopfhoerer"
info['category'] = f"{info['category']}/{info['special_attributes']['art_s']}"
del info['special_attributes']['art_s']
if "schaden_s" in info['special_attributes']:
info["category"] = f"{info['category']}/{info['special_attributes']['art_s']}"
del info["special_attributes"]["art_s"]
if "schaden_s" in info["special_attributes"]:
# change f to 'nein' and 't' to 'ja'
info['special_attributes']['schaden_s'] = info['special_attributes']['schaden_s'].translate(str.maketrans({'t': 'ja', 'f': 'nein'}))
info['price'], info['price_type'] = await self._extract_pricing_info_from_ad_page()
info['shipping_type'], info['shipping_costs'], info['shipping_options'] = await self._extract_shipping_info_from_ad_page()
info['sell_directly'] = await self._extract_sell_directly_from_ad_page()
info['images'] = await self._download_images_from_ad_page(directory, ad_id)
info['contact'] = await self._extract_contact_from_ad_page()
info['id'] = ad_id
info["special_attributes"]["schaden_s"] = info["special_attributes"]["schaden_s"].translate(str.maketrans({"t": "ja", "f": "nein"}))
info["price"], info["price_type"] = await self._extract_pricing_info_from_ad_page()
info["shipping_type"], info["shipping_costs"], info["shipping_options"] = await self._extract_shipping_info_from_ad_page()
info["sell_directly"] = await self._extract_sell_directly_from_ad_page()
info["images"] = await self._download_images_from_ad_page(directory, ad_id)
info["contact"] = await self._extract_contact_from_ad_page()
info["id"] = ad_id
try: # try different locations known for creation date element
creation_date = await self.web_text(By.XPATH,
'/html/body/div[1]/div[2]/div/section[2]/section/section/article/div[3]/div[2]/div[2]/div[1]/span')
"/html/body/div[1]/div[2]/div/section[2]/section/section/article/div[3]/div[2]/div[2]/div[1]/span")
except TimeoutError:
creation_date = await self.web_text(By.CSS_SELECTOR, '#viewad-extra-info > div:nth-child(1) > span:nth-child(2)')
creation_date = await self.web_text(By.CSS_SELECTOR, "#viewad-extra-info > div:nth-child(1) > span:nth-child(2)")
# convert creation date to ISO format
created_parts = creation_date.split('.')
creation_date = created_parts[2] + '-' + created_parts[1] + '-' + created_parts[0] + ' 00:00:00'
created_parts = creation_date.split(".")
creation_date = created_parts[2] + "-" + created_parts[1] + "-" + created_parts[0] + " 00:00:00"
creation_date = datetime.fromisoformat(creation_date).isoformat()
info['created_on'] = creation_date
info['updated_on'] = None # will be set later on
info["created_on"] = creation_date
info["updated_on"] = None # will be set later on
# Calculate the initial hash for the downloaded ad
info['content_hash'] = calculate_content_hash(info)
info["content_hash"] = calculate_content_hash(info)
return info
@@ -346,12 +346,12 @@ class AdExtractor(WebScrapingMixin):
:return: a category string of form abc/def, where a-f are digits
"""
category_line = await self.web_find(By.ID, 'vap-brdcrmb')
category_first_part = await self.web_find(By.CSS_SELECTOR, 'a:nth-of-type(2)', parent = category_line)
category_second_part = await self.web_find(By.CSS_SELECTOR, 'a:nth-of-type(3)', parent = category_line)
cat_num_first = category_first_part.attrs['href'].split('/')[-1][1:]
cat_num_second = category_second_part.attrs['href'].split('/')[-1][1:]
category:str = cat_num_first + '/' + cat_num_second
category_line = await self.web_find(By.ID, "vap-brdcrmb")
category_first_part = await self.web_find(By.CSS_SELECTOR, "a:nth-of-type(2)", parent = category_line)
category_second_part = await self.web_find(By.CSS_SELECTOR, "a:nth-of-type(3)", parent = category_line)
cat_num_first = category_first_part.attrs["href"].split("/")[-1][1:]
cat_num_second = category_second_part.attrs["href"].split("/")[-1][1:]
category:str = cat_num_first + "/" + cat_num_second
return category
@@ -368,7 +368,7 @@ class AdExtractor(WebScrapingMixin):
special_attributes_str = belen_conf["universalAnalyticsOpts"]["dimensions"]["dimension108"]
special_attributes = dict(item.split(":") for item in special_attributes_str.split("|") if ":" in item)
special_attributes = {k: v for k, v in special_attributes.items() if not k.endswith('.versand_s') and k != "versand_s"}
special_attributes = {k: v for k, v in special_attributes.items() if not k.endswith(".versand_s") and k != "versand_s"}
return special_attributes
async def _extract_pricing_info_from_ad_page(self) -> tuple[float | None, str]:
@@ -378,24 +378,24 @@ class AdExtractor(WebScrapingMixin):
:return: the price of the offer (optional); and the pricing type
"""
try:
price_str:str = await self.web_text(By.ID, 'viewad-price')
price_str:str = await self.web_text(By.ID, "viewad-price")
price:int | None = None
match price_str.split()[-1]:
case '€':
price_type = 'FIXED'
case "€":
price_type = "FIXED"
# replace('.', '') is to remove the thousands separator before parsing as int
price = int(price_str.replace('.', '').split()[0])
case 'VB':
price_type = 'NEGOTIABLE'
price = int(price_str.replace(".", "").split()[0])
case "VB":
price_type = "NEGOTIABLE"
if price_str != "VB": # can be either 'X € VB', or just 'VB'
price = int(price_str.replace('.', '').split()[0])
case 'verschenken':
price_type = 'GIVE_AWAY'
price = int(price_str.replace(".", "").split()[0])
case "verschenken":
price_type = "GIVE_AWAY"
case _:
price_type = 'NOT_APPLICABLE'
price_type = "NOT_APPLICABLE"
return price, price_type
except TimeoutError: # no 'commercial' ad, has no pricing box etc.
return None, 'NOT_APPLICABLE'
return None, "NOT_APPLICABLE"
async def _extract_shipping_info_from_ad_page(self) -> tuple[str, float | None, list[str] | None]:
"""
@@ -403,17 +403,17 @@ class AdExtractor(WebScrapingMixin):
:return: the shipping type, and the shipping price (optional)
"""
ship_type, ship_costs, shipping_options = 'NOT_APPLICABLE', None, None
ship_type, ship_costs, shipping_options = "NOT_APPLICABLE", None, None
try:
shipping_text = await self.web_text(By.CLASS_NAME, 'boxedarticle--details--shipping')
shipping_text = await self.web_text(By.CLASS_NAME, "boxedarticle--details--shipping")
# e.g. '+ Versand ab 5,49 €' OR 'Nur Abholung'
if shipping_text == 'Nur Abholung':
ship_type = 'PICKUP'
elif shipping_text == 'Versand möglich':
ship_type = 'SHIPPING'
elif '€' in shipping_text:
shipping_price_parts = shipping_text.split(' ')
ship_type = 'SHIPPING'
if shipping_text == "Nur Abholung":
ship_type = "PICKUP"
elif shipping_text == "Versand möglich":
ship_type = "SHIPPING"
elif "€" in shipping_text:
shipping_price_parts = shipping_text.split(" ")
ship_type = "SHIPPING"
ship_costs = float(misc.parse_decimal(shipping_price_parts[-2]))
# reading shipping option from kleinanzeigen
@@ -425,7 +425,7 @@ class AdExtractor(WebScrapingMixin):
internal_shipping_opt = [x for x in shipping_costs if x["priceInEuroCent"] == ship_costs * 100]
if not internal_shipping_opt:
return 'NOT_APPLICABLE', ship_costs, shipping_options
return "NOT_APPLICABLE", ship_costs, shipping_options
# map to internal shipping identifiers used by kleinanzeigen-bot
shipping_option_mapping = {
@@ -440,13 +440,13 @@ class AdExtractor(WebScrapingMixin):
"HERMES_004": "Hermes_L"
}
shipping_option = shipping_option_mapping.get(internal_shipping_opt[0]['id'])
shipping_option = shipping_option_mapping.get(internal_shipping_opt[0]["id"])
if not shipping_option:
return 'NOT_APPLICABLE', ship_costs, shipping_options
return "NOT_APPLICABLE", ship_costs, shipping_options
shipping_options = [shipping_option]
except TimeoutError: # no pricing box -> no shipping given
ship_type = 'NOT_APPLICABLE'
ship_type = "NOT_APPLICABLE"
return ship_type, ship_costs, shipping_options
@@ -457,7 +457,7 @@ class AdExtractor(WebScrapingMixin):
:return: a boolean indicating whether the sell directly option is active (optional)
"""
try:
buy_now_is_active:bool = 'Direkt kaufen' in (await self.web_text(By.ID, 'payment-buttons-sidebar'))
buy_now_is_active:bool = "Direkt kaufen" in (await self.web_text(By.ID, "payment-buttons-sidebar"))
return buy_now_is_active
except TimeoutError:
return None
@@ -469,34 +469,34 @@ class AdExtractor(WebScrapingMixin):
:return: a dictionary containing the address parts with their corresponding values
"""
contact:dict[str, (str | None)] = {}
address_text = await self.web_text(By.ID, 'viewad-locality')
address_text = await self.web_text(By.ID, "viewad-locality")
# format: e.g. (Beispiel Allee 42,) 12345 Bundesland - Stadt
try:
street = (await self.web_text(By.ID, 'street-address'))[:-1] # trailing comma
contact['street'] = street
street = (await self.web_text(By.ID, "street-address"))[:-1] # trailing comma
contact["street"] = street
except TimeoutError:
LOG.info('No street given in the contact.')
LOG.info("No street given in the contact.")
(zipcode, location) = address_text.split(" ", 1)
contact['zipcode'] = zipcode # e.g. 19372
contact['location'] = location # e.g. Mecklenburg-Vorpommern - Steinbeck
contact["zipcode"] = zipcode # e.g. 19372
contact["location"] = location # e.g. Mecklenburg-Vorpommern - Steinbeck
contact_person_element:Element = await self.web_find(By.ID, 'viewad-contact')
name_element = await self.web_find(By.CLASS_NAME, 'iconlist-text', parent = contact_person_element)
contact_person_element:Element = await self.web_find(By.ID, "viewad-contact")
name_element = await self.web_find(By.CLASS_NAME, "iconlist-text", parent = contact_person_element)
try:
name = await self.web_text(By.TAG_NAME, 'a', parent = name_element)
name = await self.web_text(By.TAG_NAME, "a", parent = name_element)
except TimeoutError: # edge case: name without link
name = await self.web_text(By.TAG_NAME, 'span', parent = name_element)
contact['name'] = name
name = await self.web_text(By.TAG_NAME, "span", parent = name_element)
contact["name"] = name
if 'street' not in contact:
contact['street'] = None
if "street" not in contact:
contact["street"] = None
try: # phone number is unusual for non-professional sellers today
phone_element = await self.web_find(By.ID, 'viewad-contact-phone')
phone_number = await self.web_text(By.TAG_NAME, 'a', parent = phone_element)
contact['phone'] = ''.join(phone_number.replace('-', ' ').split(' ')).replace('+49(0)', '0')
phone_element = await self.web_find(By.ID, "viewad-contact-phone")
phone_number = await self.web_text(By.TAG_NAME, "a", parent = phone_element)
contact["phone"] = "".join(phone_number.replace("-", " ").split(" ")).replace("+49(0)", "0")
except TimeoutError:
contact['phone'] = None # phone seems to be a deprecated feature (for non-professional users)
contact["phone"] = None # phone seems to be a deprecated feature (for non-professional users)
# also see 'https://themen.kleinanzeigen.de/hilfe/deine-anzeigen/Telefon/
return contact