【发布时间】：2022-09-23 17:26:30
【问题描述】：
我有 links.csv 文件，我使用 pd.read_csv 来一一获取这些链接。我的 csv 文件看起来像这样：https://im.ge/i/1i38PY
除了第四个链接，我可以根据我的第一个代码实时删除将我带到该站点的链接中的所有信息。数据直接保存在 mysql CARFINAL 表中，如下所示：https://im.ge/i/1igBaG
我为第四个链接得到的错误是 this-> TypeError: not enough arguments for format string ///// print(df) 看起来像这样 -> https://im.ge/i/1i8tgT
这是我在底部的第一个代码；
cursor = scrap_db.cursor()
# Drop table as per requirement
# cursor.execute(\'DROP TABLE IF EXISTS CARFINAL\')
# Create table as per requirement
sql = \"\"\"CREATE TABLE CARFINAL(
brand VARCHAR(120),
model VARCHAR(120),
model_version VARCHAR(120),
location VARCHAR(60),
price VARCHAR(80),
dealer VARCHAR(60),
contact_name VARCHAR(60),
tel_number VARCHAR(50),
mileage VARCHAR(50),
gearbox VARCHAR(60),
first_registration VARCHAR(30),
fuel_type VARCHAR(120),
power VARCHAR(60),
seller VARCHAR(60),
body_type VARCHAR(30),
type VARCHAR(10),
drivetrain VARCHAR(10),
seats int(11),
doors int(11),
country_version VARCHAR(20),
offer_number VARCHAR(20),
model_code int(11),
production_date int(11),
general_inspection int(11),
previous_owner int(11),
full_service_history VARCHAR(10),
non_smoker_vehicle VARCHAR(10),
engine_size VARCHAR(20),
gears VARCHAR(10),
cylinders VARCHAR(10),
fuel_consumption VARCHAR(60),
CO2_emissions VARCHAR(30),
energy_efficiency_class VARCHAR(10),
CO2_efficiency VARCHAR(80),
emission_class VARCHAR(20),
emissions_sticker VARCHAR(10),
colour_and_upholstery VARCHAR(60),
all_equipment VARCHAR(300),
vehicle_description VARCHAR(400),
car_picture_link VARCHAR(200),
link VARCHAR(200)
)\"\"\"
cursor.execute(sql)
#Save data to the table
#scrap_db = pymysql.connect(host=\'localhost\',user=\'root\',password=\'****\',database=\'autoscout\',charset=\'utf8mb4\',cursorclass=pymysql.cursors.DictCursor)
mySql_insert_query = \"\"\"INSERT INTO CARFINAL
(brand,
model,
model_version,
location,
price,
dealer,
contact_name,
tel_number,
mileage,
gearbox,
first_registration,
fuel_type,
power,
seller,
body_type,
type,
drivetrain,
seats,
doors,
country_version,
offer_number,
model_code,
production_date,
general_inspection,
previous_owner,
full_service_history,
non_smoker_vehicle,
engine_size,
gears,
cylinders,
fuel_consumption,
CO2_emissions,
energy_efficiency_class,
CO2_efficiency,
emission_class,
emissions_sticker,
colour_and_upholstery,
all_equipment,
vehicle_description,
car_picture_link,
link
)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s) \"\"\"
for row_count in range(0, df.shape[0]): # range(0,1)
chunk = df.iloc[row_count:row_count + 1,:].values.tolist()
tuple_of_tuples = tuple(tuple(x) for x in chunk)
cursor = scrap_db.cursor()
cursor.executemany(mySql_insert_query, tuple_of_tuples)
scrap_db.commit()
print(cursor.rowcount, \"Record inserted successfully into CARFINAL table\")
scrap_db.close()
len_of_links = len(make_model_ads_data_latest)
number = np.arange(4,5)
j = 0
for i in tqdm(number):
ad_link = make_model_ads_data_latest[\'ad_link\'][i]
#ad_link = make_model_ads_data_latest[\'ad_link\'][i+1] #BAK
if ad_link not in make_model_ads_data[\'link\'].values:
data = get_ad_data(ad_link = ad_link, sleep_time = 0)
j = j + 1
print(\"scraped \", j, \" new ads\")
顺便说一句，如果我使用我的 2. 代码；有用。我刚刚将我的第一个代码替换为这样的东西； ......
sql = \"\"\"CREATE TABLE CAR2(
brand VARCHAR(120),
model VARCHAR(120),
model_version VARCHAR(120),
location VARCHAR(60),
price VARCHAR(80),
dealer VARCHAR(60),
contact_name VARCHAR(60),
tel_number VARCHAR(50),
mileage VARCHAR(50),
gearbox VARCHAR(60),
first_registration VARCHAR(30),
fuel_type VARCHAR(120),
power VARCHAR(60),
seller VARCHAR(60),
body_type VARCHAR(30),
type VARCHAR(10),
seats int(11),
doors int(11),
country_version VARCHAR(20),
model_code VARCHAR(20),
engine_size VARCHAR(20),
colour_and_upholstery VARCHAR(30),
all_equipment VARCHAR(300),
vehicle_description VARCHAR(400),
car_picture_link VARCHAR(200),
link VARCHAR(200)
)\"\"\"
cursor.execute(sql)
#Save data to the table
#scrap_db = pymysql.connect(host=\'localhost\',user=\'root\',password=\'1234\',database=\'autoscout\',charset=\'utf8mb4\',cursorclass=pymysql.cursors.DictCursor)
mySql_insert_query = \"\"\"INSERT INTO CAR2
(brand,
model,
model_version,
location,
price,
dealer,
contact_name,
tel_number,
mileage,
gearbox,
first_registration,
fuel_type,
power,
seller,
body_type,
type,
seats,
doors,
country_version,
model_code,
engine_size,
colour_and_upholstery,
all_equipment,
vehicle_description,
car_picture_link,
link
)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s) \"\"\"
但是我不想每次刮的时候都改变结构
我被困。请帮忙
标签： python mysql pandas dataframe web-scraping