MySQL database error using scrapy

Question

I am trying to save scrapped data in MySQL database. My script.py is

 # -*- coding: utf-8 -*-
import scrapy
import unidecode
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from lxml import html


class ElementSpider(scrapy.Spider):
    name = 'books'
    download_delay = 3
    allowed_domains = ["goodreads.com"]
    start_urls = ["https://www.goodreads.com/list/show/19793.I_Marked_My_Calendar_For_This_Book_s_Release",]

    rules = (Rule(LinkExtractor(allow=(), restrict_xpaths=('//a[@class="next_page"]',)), callback="parse", follow= True),)

    def parse(self, response):
        for href in response.xpath('//div[@id="all_votes"]/table[@class="tableList js-dataTooltip"]/tr/td[2]/div[@class="js-tooltipTrigger tooltipTrigger"]/a/@href'):       
            full_url = response.urljoin(href.extract())
            print full_url
            yield scrapy.Request(full_url, callback = self.parse_books)
            break;


        next_page = response.xpath('.//a[@class="next_page"]/@href').extract()
        if next_page:
            next_href = next_page[0]
            next_page_url = 'https://www.goodreads.com' + next_href
            print next_page_url
            request = scrapy.Request(next_page_url, self.parse)
            yield request

    def parse_books(self, response):
        yield{
            'url': response.url,
            'title':response.xpath('//div[@id="metacol"]/h1[@class="bookTitle"]/text()').extract(),
            'link':response.xpath('//div[@id="metacol"]/h1[@class="bookTitle"]/a/@href').extract(),
        }

And pipeline.py is

   # -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html


import MySQLdb
import hashlib
from scrapy.exceptions import DropItem

from scrapy.http import Request
import sys

class SQLStore(object):
    def __init__(self):
        self.conn = MySQLdb.connect("localhost","root","","books" )
        self.cursor = self.conn.cursor()
        print "connected to DB"

    def process_item(self, item, spider):
        print "hi"

        try:
            self.cursor.execute("""INSERT INTO books_data(next_page_url) VALUES (%s)""", (item['url']))
            self.conn.commit()

        except Exception, e:
            print e

When i run the script there is no error. Spider running well but I think cursor not points to process_item. Even it not print hi.

Padraic Cunningham · Accepted Answer · 2016-09-21 10:19:42Z

2

Your method signature is wrong, it should take item and spider parameters:

process_item(self, item, spider)

Also you need to have the pipeline setup in your settings.py file:

 ITEM_PIPELINES = {"project_name.path.SQLStore"}

Your syntax is also incorrect, you need to pass a tuple:

  self.cursor.execute("""INSERT INTO books_data(next_page_url) VALUES (%s)""", 
    (item['url'],) # <- add ,

edited Sep 21, 2016 at 10:19

answered Sep 21, 2016 at 9:31

Padraic Cunningham

181k30 gold badges264 silver badges327 bronze badges

Sign up to request clarification or add additional context in comments.

20 Comments

V.Khakhil Over a year ago

Already have tried this but not working. I added pipeline in setting.py like this ITEM_PIPELINES = { 'test1.pipelines.SQLStore': 300, }

Padraic Cunningham Over a year ago

What is in your init.py file in your piplines directory? Also do you have process_item(self, item, spider)?

Padraic Cunningham Over a year ago

Then how does scrapy find your SQLStore pipeline?

Padraic Cunningham Over a year ago

I mean is your file actually called pipeline or pipelines? You have pipeline in your question and pipelines above. Also where do you yield any items?

V.Khakhil Over a year ago

well look at my pipeline.py when I print something inside def __init__(self): and when i print inside def process_item(self): it prints nothing. means def process_item(self): not callable.

|

Collectives™ on Stack Overflow

MySQL database error using scrapy

1 Answer 1

20 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

20 Comments

Your Answer

Sign up or log in

Post as a guest

Related