Search code examples
pythonpython-3.xscrapyscrapy-pipeline

How To Keep/Export Field Items in Specific Order Per Spider Class Definition, Utilizing The Items Pipeline in Scrapy


I have a spider which exports data to different CSV files (per the names of the class definitions as defined in the spider class). However, I also wanted to keep the order of the fields in a specific order as they were being processed and exported into their different CSV files.

For example, this is my items.py:

import scrapy

class first_class_def_Item(scrapy.Item):
    f1 = scrapy.Field() # f1 an arbitrary id used for both class definition items
    f2 = scrapy.Field()
    f3 = scrapy.Field()

class second_class_def_Item(scrapy.Item):
    f1 = scrapy.Field()
    f4 = scrapy.Field()
    f5 = scrapy.Field()
    f6 = scrapy.Field()

This is my pipelines.py:

from scrapy.exporters import CsvItemExporter
from scrapy import signals
from pydispatch import dispatcher


def item_type(item):
    # The CSV file names are used (imported) from the scrapy spider.
    # For this example, I just want to keep "first_class_def.csv" without,
    # the "_item", as in "first_class_def_Item.csv" as defined in the main scrapy spider
    return type(item).__name__.replace('_Item','')

class SomeSitePipeline(object):
    # For simplicity, I'm using the same class def names as found in the,
    # main scrapy spider and as defined in the items.py
    SaveTypes = ['first_class_def','second_class_def']

    def __init__(self):
        dispatcher.connect(self.spider_opened, signal=signals.spider_opened)
        dispatcher.connect(self.spider_closed, signal=signals.spider_closed)

    def spider_opened(self, spider):
        self.files = dict([ (name, open("/somefolder/"+name+'.csv','wb')) for name in self.SaveTypes ])
        self.exporters = dict([ (name,CsvItemExporter(self.files[name])) for name in self.SaveTypes ])
        [e.start_exporting() for e in self.exporters.values()]

    def spider_closed(self, spider):
        [e.finish_exporting() for e in self.exporters.values()]
        [f.close() for f in self.files.values()]

    def process_item(self, item, spider):
        typesItem = item_type(item)
        if typesItem in set(self.SaveTypes):
            self.exporters[typesItem].export_item(item)
        return item

And this is my spider.py:

import os
import scrapy
from itertools import zip_longest
from somesite.items import first_class_def_Item, second_class_def_Item
from csv import DictReader

path = os.path.join(os.path.expanduser('~'), 'user', 'somefolder', 'IDs.csv')

class SomeSiteSpider(scrapy.Spider):
    name = 'somesite'
    allowed_domains = ['somesite.com']
    start_urls = ['https://somesite.com/login.aspx']

    def parse(self, response):

        return scrapy.FormRequest.from_response(response,
                            formdata={'txtLogin$txtInput': 'User',
                                      'txtPassword$txtInput': 'pass',
                                      'btnLogin.x': '53',
                                      'btnLogin.y': '33'},
                            callback=self.Tables)

    def Tables(self, response):

        with open(path) as rows:

            for row in DictReader(rows):

                id=row["id"]

            yield scrapy.Request("https://somesite.com/page1.aspx",
                meta={'mid': mid,
                      'form_control': some_form_control},
                dont_filter = True,
                callback=self.first_class_def)

            yield scrapy.Request("https://somesite.com/page2.aspx",
                meta={'mid': mid,
                      'form_control': some_form_control},
                dont_filter = True,
                callback=self.second_class_def)

    def first_class_def(self, response):

        return scrapy.FormRequest.from_response(response,
                    formdata={'id': response.meta['id'],
                              'form_control': response.meta['some_form_control'],
                              'SearchControl$btnCreateReport': 'Create Report'},
                    meta={'id': response.meta['id']},
                    callback=self.scrap_page_1)

    def scrap_page_1(self, response):
        items = first_class_def_Item()

        field_1 = response.xpath('//*[@class="formatText"][1]/text()').extract()
        field_2 = response.xpath('//*[@class="formatCurrency"][1]/text()').extract()

        for a,b in zip(field_1,field_2):
            items['f1'] = response.meta['id']
            items['f2'] = a
            items['f3'] = b

            yield items

    def second_class_def(self, response):

        return scrapy.FormRequest.from_response(response,
                    formdata={'id': response.meta['id'],
                              'form_control': response.meta['some_form_control'],
                              'form_control_two': 'some_form_control_two',
                              'SearchControl$btnCreateReport': 'Create Report'},
                    meta={'id': response.meta['id']},
                    callback=self.scrap_page_2)

    def scrap_page_2(self, response):
        items = second_class_def_Item()

        field_1 = response.xpath('//*[@class="formatText"][1]/text()').extract()
        field_2 = response.xpath('//*[@class="formatCurrency"][1]/text()').extract()
        field_3 = response.xpath('//*[@class="formatText"][3]/text()').extract()

        for a,b,c in zip(field_1,field_2,field_3):
            items['f1'] = response.meta['id']
            items['f4'] = a
            items['f5'] = b
            items['f6'] = c

            yield items

As the spider was processing and exporting data, I was looking for a way to keep the fields in the CSV generated files "first_class_def.csv" and "second_class_def.csv", exported in the same order as in the items.py:

f1,f2,f3

and

f1,f4,f5,f6

However, whenever I would crawl the spider, the fields within the CSV files were being exported in random order:

f2,f1,f3 and f5,f1,f4,f6

The solution is posted below!


Solution

  • This is the solution to my specific problem: export fields organized per the items class definition as defined in the items.py of a scrapy spider project.

    So after tinkering with this problem and implementing @stranac's suggestion of getting rid of the list comprehension, I came up with the following solution, allowing to export all fields in order into their relative csv files:

    from scrapy.exporters import CsvItemExporter
    from scrapy import signals
    from pydispatch import dispatcher
    
    
    def item_type(item):
        # just want "first_class_def.csv" not "first_class_def_Item.csv"
        return type(item).__name__.replace('_Item','')
    
    class SomeSitePipeline(object):
        fileNamesCsv = ['first_class_def','second_class_def']
    
        def __init__(self):
            self.files = {}
            self.exporters = {}
            dispatcher.connect(self.spider_opened, signal=signals.spider_opened)
            dispatcher.connect(self.spider_closed, signal=signals.spider_closed)
    
        def spider_opened(self, spider):
            self.files = dict([ (name, open("/somefolder/"+name+'.csv','wb')) for name in self.fileNamesCsv ])
            for name in self.fileNamesCsv:
                self.exporters[name] = CsvItemExporter(self.files[name])
    
                if name == 'first_class_def':
                    self.exporters[name].fields_to_export = ['f1','f2','f3']
                    self.exporters[name].start_exporting()
    
                if name == 'second_class_def':
                    self.exporters[name].fields_to_export = ['f1','f4','f5','f6']
                    self.exporters[name].start_exporting()
    
        def spider_closed(self, spider):
            [e.finish_exporting() for e in self.exporters.values()]
            [f.close() for f in self.files.values()]
    
        def process_item(self, item, spider):
            typesItem = item_type(item)
            if typesItem in set(self.fileNamesCsv):
                self.exporters[typesItem].export_item(item)
            return item
    

    Now, everything works as I originally intended to.