def parse_details(self, response, item):
# script_obj = json.loads(response.xpath(SCRIPT_OBJ_XPATH).get())
try:
script_obj = chompjs.parse_js_object(response.css(SCRIPT_OBJ_CSS).get())
except Exception as e:
self.logger.error(f'{e} when script object parsing')
return
item['krisha_id'] = get_nested_item(script_obj, FLAT_KRISHA_ID_KEY)
item['title'] = response.xpath(FLAT_TITLE_XPATH).get()
item['seller_phone'] = None
item['views_count'] = None
item['price'] = get_nested_item(script_obj, FLAT_PRICE_KEY)
item['rooms_count'] = get_nested_item(script_obj, FLAT_ROOMS_COUNT_KEY)
item['total_area'] = get_nested_item(script_obj, FLAT_TOTAL_AREA_KEY)
item['ceiling_height'] = response.xpath(FLAT_CEILING_HEIGHT_XPATH).get()
item['region'] = get_nested_item(script_obj, FLAT_REGION_KEY)
item['city'] = get_nested_item(script_obj, FLAT_CITY_KEY)
item['address'] = get_nested_item(script_obj, FLAT_ADDRESS_KEY)
item['flat_floor'] = response.xpath(FLAT_FLOOR_XPATH).get()
item['longitude'] = get_nested_item(script_obj, FLAT_LONGITUDE_KEY)
item['attitude'] = get_nested_item(script_obj, FLAT_ATTITUDE_KEY)
item['construction_year'] = response.xpath(BUILDING_CONSTRUCTION_YEAR_XPATH).get()
item['floors_count'] = response.xpath(BUILDING_FLOORS_COUNT_XPATH).get()
item['wall_type'] = response.xpath(BUILDING_WALL_TYPE_XPATH).get()
item['seller_user_type'] = get_nested_item(script_obj, FLAT_SELLER_USER_TYPE_KEY)
item['description'] = response.xpath(FLAT_DESCRIPTION_XPATH).getall()
return item
def scrape_beer_bazaar():
base_url = 'https://beerbazaar.co.il/apps/bundles/bundle/17591'
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko)'
}
price = '8 for 99, 12 for 129'
brewery = 'Beer Bazaar'
results = []
supplier = brewery
html = urlopen(base_url).read()
soup = BeautifulSoup(html, features="html.parser")
script = soup.find('script', id='bundle-builder-app--bundle--data')
script = str(script)[506:]
beers = parse_js_object(script)
for beer in beers:
# Name
name = beer['handle']
print(name)
# Image
img = beer['image']['src']
print(img)
print('\n')
new_beer = [name, price, base_url, img, supplier, brewery]
results.append(new_beer)
return results
print(f"Finished scraping: {supplier}!")
def parse_product_details_neptun(response):
dict_item = {}
new_response = response.replace(encoding='utf-8')
result = new_response.css('script:contains(productModel)::text').get()
if result:
decoded = codecs.decode(
result, 'unicode_escape').encode('latin1').decode('utf8')
dict_data = chompjs.parse_js_object(decoded)
market_name = 'neptun'
dict_item["id"] = f'{market_name}-{dict_data["Id"]}'
dict_item['brand'] = dict_data['Manufacturer']['Name'].title()
dict_item['product_name'] = dict_data['Title'].replace("Лаптоп ", "")
dict_item['categories_path'] = [
data_['Name'] for data_ in dict_data['NavigationPath']
]
dict_item['price'] = dict_data['RegularPrice']
dict_item['discount_price'] = dict_data['DiscountPrice']
sel_desc = scrapy.selector.Selector(text=dict_data['Description'])
lst_desc_line = sel_desc.xpath('//ul/li/text()').getall()
if lst_desc_line:
lst_desc_line = [
item_.strip() for item_ in lst_desc_line if item_.strip()
]
dict_item['description'] = '\n'.join(lst_desc_line)
dict_item['url'] = response.request.url
dict_item['market_name'] = market_name
return dict_item
def test_nested_dict(self):
result = parse_js_object(
"{'hello': 'world', 'my': {'master': 'of Orion'}, 'test': 'xx'}")
self.assertEqual(result, {
'hello': 'world',
'my': {
'master': 'of Orion'
},
'test': 'xx'
})
def parse_infos(self, response):
data_string = data = response.xpath(
'//script[@id="js-hydration"]/text()').get()
data = chompjs.parse_js_object(data_string,
json_params={'strict': False})
loader = ItemLoader(ImmobiliareItem(), response)
# inspect_response(response, self)
loader.add_value('image_urls', nested_lookup('medium', data))
data = nested_delete(data, 'multimedia')
listing = nested_delete(nested_lookup('listing', data)[0], 'type')
listing = nested_delete(listing, 'title')
loader.add_value('listing', listing)
loader.add_value('trovokasa', nested_lookup('trovakasa', data))
yield loader.load_item()
def parse(self, response):
response_js = chompjs.parse_js_object(response.text)
for element in response_js.get("data"):
date = self.extract_date(element)
url = self.extract_url(element)
edition_number = self.extract_edition_number(element)
is_extra_edition = self.extract_is_extra_edition(element)
yield Gazette(
date=date,
file_urls=[url],
edition_number=edition_number,
is_extra_edition=is_extra_edition,
power="executive_legislative",
)
def test_stack(self):
result = parse_js_object(
"{'a':[{'b':1},{'c':[{'d':{'f':{'g':[1,2]}}},{'e':1}]}]}",
initial_stack_size=1,
)
self.assertEqual(
result,
{'a': [{
'b': 1
}, {
'c': [{
'd': {
'f': {
'g': [1, 2]
}
}
}, {
'e': 1
}]
}]})
def parse(self, response):
"""Descobre datas disponíveis em calendário na página inicial e as requisita"""
available_dates_js = re.search(r"var eventData = \[.+?\];",
response.text, re.DOTALL).group()
available_dates = parse_js_object(available_dates_js)
for date_metadata in available_dates:
gazette_date = self._parse_date(date_metadata["date"])
if not (self.start_date <= gazette_date <= self.end_date):
continue
callback = (self.parse_multi_publication_date
if date_metadata["classname"] == "ambos" else
self.parse_single_publication_date)
yield scrapy.Request(
url=
f"{self.BASE_URL}doDia.php?dataEdicao={date_metadata['date']}",
callback=callback,
cb_kwargs={"date_metadata": date_metadata},
)
def parse_details(self, response):
scripts = response.css('script::text').getall()
for script in scripts:
try:
obj = chompjs.parse_js_object(script)
if 'product' in obj:
obj = obj['product']['preFetchedData']
break
except ValueError as e:
pass
data = {
'shop': 'mechta.kz',
'url': response.request.url,
'title': clean_title(obj['NAME'], 'Телефон сотовый'),
'price': obj['PRICE']['PRICE'],
'images': obj['PHOTO'],
'specs': self.get_specs(obj)
}
yield data
def parse1(self, response):
jsonresp= chompjs.parse_js_object(response.xpath("//@data-redux-state").extract_first())
for items in self.traversen(jsonresp):
loader=ItemLoader(item=TescoItem(), selector=items)
tesco_img_url=" "
tesco_prod_name=" "
tesco_img_url = items['defaultImageUrl']
tesco_prod_name = items['title']
name= self.cleanup(tesco_prod_name)
loader.add_value('image_urls', tesco_img_url)
loader.add_value('image_name', name)
yield loader.load_item()
next_url= response.xpath("//nav[@class='pagination--page-selector-wrapper']/ul/li/a[@class='pagination--button prev-next'][@aria-label='Go to results page']/@href").get()
if next_url:
next_lnk= response.urljoin(response.xpath("//nav[@class='pagination--page-selector-wrapper']/ul/li/a[@class='pagination--button prev-next'][@aria-label='Go to results page']/@href").get())
yield scrapy.Request(url=next_lnk, callback=self.parse1, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36'
},dont_filter=True)
# def parse1(self, response):
# for product in response.xpath("//ul[@class='product-list grid']/li[contains(@class,'product-list--list-item')]"):
# loader=ItemLoader(item=TescoItem(), selector=product)
# tesco_img_url = product.xpath(".//div/div/div/div/a/div/img/@srcset").get()
# #tesco_img_url = tesco[tesco.rfind("http"):tesco.rfind(" ")]
# tesco_prod_name = product.xpath(".//div[@class='product-details--wrapper']/div/h3/a/text()").get()
# print("********")
# print(tesco_img_url)
# print(tesco_prod_name)
# loader.add_value('image_urls', tesco_img_url)
# loader.add_value('image_name',tesco_prod_name)
# yield loader.load_item()
# next_url= response.xpath("//nav[@class='pagination--page-selector-wrapper']/ul/li/a[@class='pagination--button prev-next'][@aria-label='Go to results page']/@href").get()
# if next_url:
# next_lnk= response.urljoin(response.xpath("//nav[@class='pagination--page-selector-wrapper']/ul/li/a[@class='pagination--button prev-next'][@aria-label='Go to results page']/@href").get())
# yield scrapy.Request(url=next_lnk, callback=self.parse1, headers={
# 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36'
# },dont_filter=True)
def parse_category_products(self, response):
this_url = response.request.url
base_url = this_url.split('?')[0]
items_show = 100
dict_form_data = {}
dict_form_data['items'] = f'{items_show}'
new_response = response.replace(encoding='utf-8')
result = new_response.css(
'script:contains(shopCategoryModel)::text').get()
if result:
decoded = codecs.decode(
result, 'unicode_escape').encode('latin1').decode('utf8')
dict_data = chompjs.parse_js_object(decoded)
number_of_products = dict_data["NumberOfProducts"]
page_count = number_of_products // items_show
page_count = page_count + 1 if number_of_products % items_show else page_count
lst_links = [
f"{base_url}/{dict_product_['Url']}"
for dict_product_ in dict_data["Products"]
]
for link_ in lst_links:
urlItem = UrlItem()
urlItem["url"] = link_
yield urlItem
if page_count > 1:
for i in range(2, page_count + 1):
dict_form_data["page"] = i
href = f"{base_url}?{urlencode(dict_form_data)}"
yield scrapy.Request(href,
callback=self.parse_category_products)
def parse_text(
self,
response,
company_link,
title,
title_link,
date_posted,
location,
company,
):
description = self.cleanhtml(
chompjs.parse_js_object(
response.xpath("//script[contains(., 'JobPosting')]/text()").
extract()[0])["description"])
yield {
"company_link": company_link,
"job_title": title,
"link": title_link,
"activated_at": date_posted,
"job_id": uuid.uuid4(),
"location": location,
"company_name": company,
"text": description
}
def test_depth(self):
result = parse_js_object("[[[[[[[[[[[[[[[1]]]]]]]]]]]]]]]")
self.assertEqual(result, [[[[[[[[[[[[[[[1]]]]]]]]]]]]]]])
def test_multiple_identifiers(self):
result = parse_js_object("{a:1,b:1,c:1,d:1,e:1,f:1,g:1,h:1,i:1,j:1}")
self.assertEqual(result, {k: 1 for k in 'abcdefghij'})
def test_one_field_dict(self):
result = parse_js_object("{'hello': 'world'}")
self.assertEqual(result, {'hello': 'world'})
def test_escaped_text(self):
result = parse_js_object("{'a': '123\\'456\\n'}")
self.assertEqual(result, {'a': "123'456\n"})
def test_special_fields(self):
result = parse_js_object("{'a': true, 'b': false, 'c': null}")
self.assertEqual(result, {'a': True, 'b': False, 'c': None})
def test_nested_lists(self):
result = parse_js_object("[[[]]]")
self.assertEqual(result, [[[]]])
def test_dict_with_multiple_element_list(self):
result = parse_js_object("{'hello': [1, 2, 3, 4]}")
self.assertEqual(result, {'hello': [1, 2, 3, 4]})
def test_multiple_list_items_string(self):
result = parse_js_object("['h', 'e', 'l', 'l', 'o']")
self.assertEqual(result, ['h', 'e', 'l', 'l', 'o'])
def test_dict_with_lists(self):
result = parse_js_object("{'hello': [], 'world': [0]}")
self.assertEqual(result, {'hello': [], 'world': [0]})
def test_empty_dict(self):
result = parse_js_object("{}")
self.assertEqual(result, {})
def test_single_list_item(self):
result = parse_js_object("[1]")
self.assertEqual(result, [1])
def test_nested_lists_with_value(self):
result = parse_js_object("[[[1]]]")
self.assertEqual(result, [[[1]]])
def test_unicode_values(self):
result = parse_js_object("['\u00E9']")
self.assertEqual(result, ['é'])
def test_list_of_dicts(self):
result = parse_js_object("[{'a':12}, {'b':33}]")
self.assertEqual(result, [{'a': 12}, {'b': 33}])
def test_unicode_keys(self):
result = parse_js_object('{"cache":{"\u002Ftest\u002F": 0}}')
self.assertEqual(result, {'cache': {'/test/': 0}})
def test_non_quoted_identifier(self):
result = parse_js_object("{abcdefghijklmnopqrstuvwxyz: 12}")
self.assertEqual(result, {"abcdefghijklmnopqrstuvwxyz": 12})
def test_multiple_list_items(self):
result = parse_js_object("[1, 2, 3, 4]")
self.assertEqual(result, [1, 2, 3, 4])
def test_empty_list(self):
result = parse_js_object("[]")
self.assertEqual(result, [])
