Added SqlitePostPipeline

This commit is contained in:
ayxan 2022-09-08 21:32:42 +04:00
parent fa1eba8e49
commit f321447fea
4 changed files with 116 additions and 10 deletions

3
.gitignore vendored
View File

@ -1,4 +1,5 @@
__pycache__
.venv
cars.jl
cars.csv
cars.csv
cars.db

View File

@ -1,6 +1,113 @@
from itemadapter import ItemAdapter
import sqlite3
class PostScrapePipeline:
class SqlitePostPipeline:
def __init__(self):
self.id = 1
self.con = sqlite3.connect('cars.db')
self.cur = self.con.cursor()
self.cur.execute("""
CREATE TABLE IF NOT EXISTS cars(
id INTEGER,
url TEXT,
avto_salon TEXT,
description TEXT,
city TEXT,
brand TEXT,
model TEXT,
year INTEGER,
category TEXT,
color TEXT,
engine_volume INTEGER,
engine_power INTEGER,
fuel_type TEXT,
mileage INTEGER,
mileage_type TEXT,
transmission TEXT,
gear TEXT,
price INTEGER,
currency TEXT,
loan TEXT,
barter TEXT,
market TEXT,
seats_count TEXT,
prior_owners_count TEXT,
crashed TEXT,
painted TEXT
)
""")
# IMAGE
self.cur.execute("""
CREATE TABLE IF NOT EXISTS images(
post_id INTEGER,
url TEXT
)
""")
# PHONE
self.cur.execute("""
CREATE TABLE IF NOT EXISTS phones(
post_id INTEGER,
phone TEXT
)
""")
# EXTRA_FIELDS
self.cur.execute("""
CREATE TABLE IF NOT EXISTS extra_fields(
post_id INTEGER,
extra_field TEXT
)
""")
self.cur.execute("SELECT * FROM cars ORDER BY id DESC LIMIT 1")
result = self.cur.fetchone()
if result is not None: self.id = result[0] + 1
def process_item(self, item, spider):
self.cur.execute("""
INSERT INTO cars (id, url, avto_salon, description, city, brand, model, year, category, color, engine_volume, engine_power, fuel_type, mileage, mileage_type, transmission, gear, price, currency, loan, barter, market, seats_count, prior_owners_count, crashed, painted) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
""",
(
self.id,
item['url'],
item['avto_salon'],
' '.join(item['description']),
item['city'],
item['brand'],
item['model'],
item['year'],
item['category'],
item['color'],
item['engine_volume'],
item['engine_power'],
item['fuel_type'],
item['mileage'],
item['mileage_type'],
item['transmission'],
item['gear'],
item['price'],
item['currency'],
item['loan'],
item['barter'],
item['market'],
item['seats_count'],
item['prior_owners_count'],
item['crashed'],
item['painted']
))
# IMAGE
for image in item['images']:
self.cur.execute("""INSERT INTO images (post_id, url) VALUES (?, ?)""",
(self.id, image))
# PHONE
for phone in item['phone']:
self.cur.execute("""INSERT INTO phones (post_id, phone) VALUES (?, ?)""",
(self.id, phone))
# EXTRA_FIELDS
for field in item['extra_fields']:
self.cur.execute("""INSERT INTO extra_fields (post_id, extra_field) VALUES (?, ?)""",
(self.id, field))
self.con.commit()
self.id += 1
return item

View File

@ -60,11 +60,9 @@ ROBOTSTXT_OBEY = True
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'post_scrape.pipelines.PostScrapePipeline': 300,
#}
# ITEM_PIPELINES = {
# 'post_scrape.pipelines.SqlitePostPipeline': 300,
# }
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html

View File

@ -6,8 +6,8 @@ class CarDataSpider(Spider):
name = "turbo.az"
allowed_domains = ('turbo.az',)
headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
}
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
}
def __init__(self, first_page=1, last_page=2, *args, **kwargs):
super(CarDataSpider, self).__init__(*args, **kwargs)