def get_format_product(url, product_model):
try:
html_str = get_html(url)
products = []
products_container = html_str.find(attrs={"class": "mProList"})
if products_container:
products_div = products_container.findAll(attrs={"class": "l"})
for product_div in products_div:
product = {}
product_name_a = product_div.find("a")
product_index_href = product_name_a.attrs["href"]
product_index_name = product_name_a.text
product_descs_lis = product_div.findAll("li")
for product_descs_li in product_descs_lis:
key = product_descs_li.find("i").text
value = product_descs_li.find("span").text
product[key.strip()] = value.strip()
product['product_index_href'] = product_index_href
product['product_index_name'] = product_index_name
product['_id'] = get_next_id(product_model)
product['version'] = current_version
products.append(product)
return products
except BaseException as e:
print('错误：', e)
except_handler(url, product_model)
return []
def che360_engine_clean():
has_next = True
for i in range(0, 100000):
page_size = 10
coll = che360_engine_model_detail.find({}).sort(
'_id', pymongo.ASCENDING).skip(i * page_size).limit(page_size)
if not has_next:
return
has_next = False
for data in coll:
has_next = True
engine = {}
engine["desc"] = data.get("cell_model_name", "")
engine["engine_model"] = data.get("发动机：", "")
engine["series"] = data.get("系列：", "")
engine["engine_supp"] = data.get("发动机厂商：", "")
engine["cylinders_num"] = data.get("汽缸数：", "")
engine["fuel_type"] = data.get("燃料种类：", "")
engine["cc"] = data.get("排量：", "")
engine["max_power"] = data.get("最大输出功率：", "")
engine["max_hp"] = data.get("最大马力：", "")
engine["engine_type"] = data.get("发动机形式：", "")
engine["nick_name"] = data.get("nick_name", "")
engine["_id"] = get_next_id("engine_model_detail")
print(engine)
print()
engine_model_detail.insert_one(engine)
def get_format_product_detail(parent_collection, detail_collection, version):
models_josn = truck_parts_db[parent_collection].find({
"version": version
}, {
"_id": 1,
"product_index_href": 1,
"version": 1
}).distinct('product_index_href')
for model in models_josn:
model_index_url = model
# ["product_index_href"]
model_param_url = model_index_url.replace("index", "param")
url = "https://product.360che.com" + model_param_url
print(url)
html = get_html(url)
product_detail_container = html.find(attrs={"class": "parameter-detail"})
product_detail_num = sum(1 for _ in product_detail_container.find(
"tr",
attrs={
"id": "fixed_top"
},
).findAll("th"))
product_details = {}
for i in range(1, product_detail_num):
product_details[i] = {}
rows = product_detail_container.findAll("tr")
for row_data in rows:
if row_data.get('id', "") == "fixed_top":
for i in range(1, product_detail_num):
cell_model_name = row_data.findAll("th")[i].find(
'a').string
product_details[i]["cell_model_name"] = cell_model_name
if row_data.get('class', "") == ["param-row"]:
row_id = row_data.findAll("td")[0].text
for i in range(1, product_detail_num):
value_content_td = row_data.findAll("td")
if value_content_td and len(value_content_td) > i:
value_content = value_content_td[i]
if value_content:
value = value_content.find('div').text
product_details[i][row_id] = value.strip()
for product_details in product_details.values():
product_details["_id"] = get_next_id('filter_model_detail')
product_details["parent_id"] = model
product_details["version"] = version
truck_parts_db[detail_collection].insert(product_details)
query = {"product_index_href": model}
newvalues = {"$set": {"version": version + 1}}
update_ret = truck_parts_db[parent_collection].update_many(query, newvalues)
print(update_ret.modified_count)
def __init__(self, name, contact_email, description, image_url, zip_code,
latitude, longitude, instructions, address, accepts_opened,
city, state):
self.id = utils.get_next_id()
self.name = name
self.contact_email = contact_email
self.description = description
self.image_url = image_url
self.zip_code = zip_code
self.latitude = latitude
self.longitude = longitude
self.instructions = instructions
self.address = address
self.accepts_opened = accepts_opened
self.city = city
self.state = state
def eurocvbay_parts_clean():
has_next = True
for i in range(0, 100000):
page_size = 10
coll = che360_eurocvbay_parts_clean.find({}).sort(
'_id', pymongo.ASCENDING).skip(i * page_size).limit(page_size)
if not has_next:
return
has_next = False
for data in coll:
has_next = True
filter = {}
filter["_id"] = get_next_id("filter_model_detail")
filter["desc"] = data.get("product_name", "")
filter["replaces"] = data.get("replaces", "")
print(filter)
print()
def che360_truck_clean():
has_next = True
for i in range(0, 100000):
page_size = 10
coll = che360_truck_model_detail.find({}).sort(
'_id', pymongo.ASCENDING).skip(i * page_size).limit(page_size)
if not has_next:
return
has_next = False
for data in coll:
has_next = True
truck = {}
truck["desc"] = data.get("cell_model_name", "")
truck["announcement_model"] = data.get("公告型号：", "")
truck["drive_model"] = data.get("驱动形式：", "")
truck["desc"] = data.get("轴距：", "")
truck["engine_model"] = data.get("发动机：", "")
truck["transmission_model"] = data.get("变速箱：", "")
truck["length"] = data.get("车身长度：", "")
truck["width"] = data.get("车身宽度：", "")
truck["height"] = data.get("车身高度：", "")
truck["weight"] = data.get("整车重量：", "")
truck["capacity_kg"] = data.get("额定载重：", "")
truck["tonnage_level"] = data.get("吨位级别：", "")
truck["engine_brand"] = data.get("发动机品牌：", "")
truck["cylinders_num"] = data.get("汽缸数：", "")
truck["fuel_type"] = data.get("燃料种类：", "")
truck["cc"] = data.get("排量：", "")
truck["max_hp"] = data.get("最大马力：", "")
truck["max_power"] = data.get("最大输出功率：", "")
truck["engine_type"] = data.get("发动机形式：", "")
truck["transmission_brand"] = data.get("变速箱品牌：", "")
truck["forward_gears_num"] = data.get("前进挡位：", "")
truck["reverse_gears_num"] = data.get("倒挡数：", "")
truck["tyre_type"] = data.get("轮胎规格：", "")
truck["tyre_num"] = data.get("轮胎数：", "")
truck["tyre_num"] = data.get("弹簧片数：", "")
truck["brand"] = data.get("brand_name", "")
truck["model"] = data.get("model_name", "")
truck["_id"] = get_next_id("truck_model_detail")
print(truck)
print()
truck_model_detail.insert_one(truck)
def cn357_truck_clean():
has_next = True
for i in range(0, 10000):
page_size = 10
coll = cn357_truck_model_detail.find({}).sort(
'_id', pymongo.ASCENDING).skip(i * page_size).limit(page_size)
if not has_next:
return
has_next = False
for data in coll:
has_next = True
truck = {}
truck["desc"] = data.get("product", "")
truck["announcement_model"] = data.get("整车公告：", "")
truck["brand"] = data.get("品牌：", "")
truck["series"] = data.get("车系：", "")
truck["purpose"] = data.get("用途：", "")
truck["drive_model"] = data.get("驱动方式：", "")
truck["tonnage_level"] = data.get("吨位级别：", "")
truck["manufacturer"] = data.get("生产厂家：", "")
truck["origin"] = data.get("整车产地：", "")
truck["weight"] = data.get("整车重量：", "")
truck["length"] = data.get("整车长度：", "")
truck["width"] = data.get("整车宽度：", "")
truck["height"] = data.get("整车高度：", "")
truck["member"] = data.get("准乘人数：", "")
truck["engine_model"] = data.get("发动机型号：", "")
truck["engine_type"] = data.get("发动机形式：", "")
truck["max_power"] = data.get("最大功率：", "")
truck["max_hp"] = data.get("最大马力：", "")
truck["cc"] = data.get("排量：", "")
truck["fuel_type"] = data.get("燃油种类：", "")
truck["transmission_model"] = data.get("变速箱型号：", "")
truck["forward_gears_num"] = data.get("前进档位数：", "")
truck["reverse_gears_num"] = data.get("倒档档位数：", "")
truck["chassis_models"] = data.get("底盘型号：", "")
truck["plate_spring_num"] = data.get("板簧片数：", "")
truck["tyre_num"] = data.get("轮胎数量：", "")
truck["tyre_type"] = data.get("轮胎规格：", "")
truck["_id"] = get_next_id("truck_model_detail")
print(truck)
print()
truck_model_detail.insert_one(truck)
def cn357_filter_clean():
has_next = True
for i in range(0, 100000):
page_size = 10
coll = cn357_filter_model_detail.find({}).sort(
'_id', pymongo.ASCENDING).skip(i * page_size).limit(page_size)
if not has_next:
return
has_next = False
for data in coll:
has_next = True
filter = {}
filter["brand"] = data.get("品牌：", "").split("：")[1]
models_str = data.get("型号：", "").split("：")[1]
models = models_str.split("/")
for model in models:
filter["model"] = model
filter["_id"] = get_next_id("filter_model_detail")
print(filter)
filter_model_detail.insert_one(filter)
def get_format_product(url, product_model):
html_str = get_html(url)
products = []
product_list_ul = html_str.findAll(attrs={"class": "products-list"})[0]
products_li = product_list_ul.findAll("li")
for product_li in products_li:
product = {}
product_name_a = product_li.find("h5").find("a")
product_index_href = product_name_a.attrs["href"]
product_index_name = product_name_a.text
product_span = product_li.findAll(
attrs={"class": "content"})[0].find("span")
product_items = product_span.findAll("p")
for product_item in product_items:
item_type = product_item.find("span")
product[item_type.next_element.strip(
)] = item_type.next_sibling.strip()
product['product_index_href'] = product_index_href
product['product_index_name'] = product_index_name
product['_id'] = get_next_id(product_model)
product['version'] = current_version
products.append(product)
return products
def che360_filter_clean():
has_next = True
for i in range(0, 100000):
page_size = 10
coll = che360_air_filter_detail.find({}).sort(
'_id', pymongo.ASCENDING).skip(i * page_size).limit(page_size)
if not has_next:
return
has_next = False
for data in coll:
has_next = True
filter = {}
filter["_id"] = get_next_id("filter_model_detail")
filter["desc"] = data.get("cell_model_name", "")
filter["type"] = data.get("类型：", "")
filter["model"] = data.get("滤清器型号：", "")
filter["diameter"] = data.get("直径：", "")
filter["height"] = data.get("高度：", "")
filter["weight"] = data.get("重量：", "")
filter["leakproof_type"] = data.get("密封结构：", "")
filter["locating_hole_diameter"] = data.get("定位孔直径：", "")
filter["size_model"] = data.get("尺寸型号：", "")
filter["market_model"] = data.get("市场型号：", "")
filter["flux"] = data.get("流量：", "")
filter["filter_level"] = data.get("过滤级别：", "")
filter["thread_size"] = data.get("螺纹尺寸：", "")
filter["adaptable_truck_models"] = data.get("适用车型：", "").split("/")
filter["adaptable_enign_models"] = data.get("适用机型：", "").split("/")
filter["adaptable_truck_types"] = data.get("适用车类型：", "").split("/")
filter["adaptable_engine_types"] = data.get("适用发动机类型：",
"").split("/")
filter["alternative_parts_model"] = data.get("可替换滤清器型号：", "")
filter["nick_name"] = data.get("可替换滤清器零件号：", "")
print(filter)
print()
filter_model_detail.insert_one(filter)
def create_session(self):
self.session_start_time = int(time.time())
self.session_id = get_next_id()
self.session_file = os.path.join(self.upload_dir, "{}.mp3".format(self.session_id))
self.metadata_file = os.path.join(self.upload_dir, "{}.json".format(self.session_id))
logging.info("created session, session id: %d", self.session_id)
def test_get_next_id(self):
self.assertEqual(1, get_next_id())
self.assertEqual(2, get_next_id())
def create(self, user_id, text):
post_id = get_next_id()
p = db.Post(post_id, user_id, text)
p.save()
return p.post_id
def create_session(self):
self.session_start_time = int(time.time())
self.session_id = get_next_id()
self.session_file = os.path.join(self.upload_dir, '{}.mp3'.format(self.session_id))
self.metadata_file = os.path.join(self.upload_dir, '{}.json'.format(self.session_id))
logging.info('created session, session id: %d', self.session_id)
