I have a data scraped from cars.com. And am trying to save them to MySQL database and I couldn't managed to do so. Here is my full code:
#ScrapeData.py
import requests
from bs4 import BeautifulSoup
URL = "https://www.cars.com/shopping/results/?dealer_id=&keyword=&list_price_max=&list_price_min=&makes[]=&maximum_distance=all&mileage_max=&page=1&page_size=100&sort=best_match_desc&stock_type=cpo&year_max=&year_min=&zip="
r = requests.get(URL)
soup = BeautifulSoup(r.content, 'html.parser')
cars = soup.find_all('div', class_='vehicle-card')
name = []
mileage = []
dealer_name = []
rating = []
rating_count = []
price = []
for car in cars:
#name
name.append(car.find('h2').get_text())
#mileage
mileage.append(car.find('div', {'class':'mileage'}).get_text())
#dealer_name
dealer_name.append(car.find('div', {'class':'dealer-name'}).get_text())
#rate
try:
rating.append(car.find('span', {'class':'sds-rating__count'}).get_text())
except:
rating.append("n/a")
#rate_count
rating_count.append(car.find('span', {'class':'sds-rating__link'}).get_text())
#price
price.append(car.find('span', {'class':'primary-price'}).get_text())
#save_to_mysql.py
import pymysql
import scrapeData
import mysql.connector
connection = pymysql.connect(
host='localhost',
user='root',
password='',
db='cars',
)
name = scrapeData.name
mileage = scrapeData.mileage
dealer_name = scrapeData.dealer_name
rating = scrapeData.rating
rating_count = scrapeData.rating_count
price = scrapeData.price
try:
mySql_insert_query = """INSERT INTO cars_details (name, mileage, dealer_name, rating, rating_count, price)
VALUES (%s, %s, %s, %s, %s, %s) """
records_to_insert = [(name, mileage, dealer_name, rating, rating_count, price)]
print(records_to_insert)
cursor = connection.cursor()
cursor.executemany(mySql_insert_query, records_to_insert)
connection.commit()
print(cursor.rowcount, "Record inserted successfully into cars_details table")
except mysql.connector.Error as error:
print("Failed to insert record into MySQL table {}".format(error))
connection.commit()
finally:
connection.close()
whenever I run this code I get this error message:
Traceback (most recent call last):
File "c:\scraping\save_to_mysql.py", line 28, in <module>
cursor.executemany(mySql_insert_query, records_to_insert)
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\cursors.py", line 173, in executemany
return self._do_execute_many(
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\cursors.py", line 211, in _do_execute_many rows = self.execute(sql postfix)
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\cursors.py", line 148, in execute
result = self._query(query)
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\cursors.py", line 310, in _query
conn.query(q)
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\connections.py", line 548, in query
self._affected_rows = self._read_query_result(unbuffered=unbuffered)
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\connections.py", line 775, in _read_query_result
result.read()
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\connections.py", line 1156, in read
first_packet = self.connection._read_packet()
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\connections.py", line 725, in _read_packet packet.raise_for_error()
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\protocol.py", line 221, in raise_for_error err.raise_mysql_exception(self._data)
File "C:\Users\PC\AppData\Local\Programs\Python\Python310\lib\site-packages\pymysql\err.py", line 143, in raise_mysql_exception
raise errorclass(errno, errval)
pymysql.err.OperationalError: (1241, 'Operand should contain 1 column(s)')
Anybody have any idea of how to solve this? I want to insert multiple scraped data in MySQL at one execution. I will be glad for your help
CodePudding user response:
Firstly i wouldnt use seperated lists for all your data, but use a single list, with all the information about a single car gathered. So like nested within it. so instead of
millage = []
delar_name = []
i would create a single list called cars:
cars = []
Then i would create dirrerent variables for all the different pieces of scrape info you have on a car like this:
#brand
brand = car.find('h2').get_text()
#mileage
mileage = car.find('div', {'class':'mileage'}).get_text()
Then i would create the list for appending and append it to the list.
toAppend = brand, mileage, dealer_name, rating, rating_count, price
cars.append(toAppend)
Then the output would be:
[('2018 Mercedes-Benz CLA 250 Base', '21,326 mi.', '\nMercedes-Benz of South Bay\n', '4.6', '(1,020 reviews)', '$33,591'), ('2021 Toyota Highlander Hybrid XLE', '9,529 mi.', '\nToyota of Gastonia\n', '4.6', '(590 reviews)', '$47,869')]
I have made a small change to the mysql. Inserted into a function, then importing that function into the main script at just thrownin the list as a paramter. Works like a charm. I know this isnt an elaborate answer on why and how things are working, but it is a solution non the less.
import requests
from bs4 import BeautifulSoup
from scrapertestsql import insertScrapedCars
URL = "https://www.cars.com/shopping/results/?dealer_id=&keyword=&list_price_max=&list_price_min=&makes[]=&maximum_distance=all&mileage_max=&page=1&page_size=100&sort=best_match_desc&stock_type=cpo&year_max=&year_min=&zip="
r = requests.get(URL)
soup = BeautifulSoup(r.content, 'html.parser')
scrapedCars = soup.find_all('div', class_='vehicle-card')
cars = []
# mileage = []
# dealer_name = []
# rating = []
# rating_count = []
# price = []
for car in scrapedCars:
#name
brand = car.find('h2').get_text()
#mileage
mileage = car.find('div', {'class':'mileage'}).get_text()
#dealer_name
dealer_name = car.find('div', {'class':'dealer-name'}).get_text()
#rate
try:
rating = car.find('span', {'class':'sds-rating__count'}).get_text()
except:
rating = "n/a"
#rate_count
rating_count = car.find('span', {'class':'sds-rating__link'}).get_text()
#price
price = car.find('span', {'class':'primary-price'}).get_text()
toAppend = brand, mileage, dealer_name, rating, rating_count, price
cars.append(toAppend)
insertScrapedCars(cars)
print(cars)
Next i would :
import pymysql
import mysql.connector
connection = pymysql.connect(
host='127.0.0.1',
user='test',
password='123',
db='cars',
port=8889
)
def insertScrapedCars(CarsToInsert):
try:
mySql_insert_query = """INSERT INTO cars_details (name, mileage, dealer_name, rating, rating_count, price)
VALUES (%s, %s, %s, %s, %s, %s) """
cursor = connection.cursor()
cursor.executemany(mySql_insert_query, CarsToInsert)
connection.commit()
print(cursor.rowcount, "Record inserted successfully into cars_details table")
except mysql.connector.Error as error:
print("Failed to insert record into MySQL table {}".format(error))
finally:
connection.close()