XMLFeedSpider not Producing an Output CSV-CodePudding

Having an issue with XMLFeedSpider. I can get the parsing to work on the scrapy shell, so it seems there is something going on with either the request, or the spider's engagement. Whether I add a start_request() method or not, I seem to get the same error.

No output_file.csv is produced after running the spider.

I am able to get a scrapy.Spider and CrawlSpider to work, but can't seem to figure out what I am doing wrong with the XMLFeedSpider.

This is the spider:

from ..items import TheItem
from scrapy.loader import ItemLoader
import scrapy
from scrapy.crawler import CrawlerProcess


class TheSpider(scrapy.spiders.XMLFeedSpider):
    name = 'stuff_spider'
    allowed_domains = ['www.website.net']
    start_urls = ['https://www.website.net/10016/stuff/otherstuff.xml']
    namespaces = [('xsi', 'https://schemas.website.net/xml/uslm'), ]
    itertag = 'xsi:item'
    iterator = 'xml'

    def start_requests(self):
        yield scrapy.Request('https://www.website.net/10016/stuff/otherstuff.xml', callback=self.parse_node)

    def parse_node(self, response, node):
        l = ItemLoader(item=TheItem(), selector=node, response=response)

        just_want_something = 'just want the csv to show some output'

        l.add_xpath('title', response.xpath('//xsi:title/text()').extract())
        l.add_xpath('date', response.xpath('//xsi:date/text()').extract())
        l.add_xpath('category', node.xpath('//xsi:cat1/text()').extract())
        l.add_value('content', node.xpath('//xsi:content/text()'))
        l.add_value('manditory', just_want_something)

        yield l.load_item()


process = CrawlerProcess(settings={
    'FEEDS': 'output_file.csv',
    'FEED_FORMAT': 'csv',
    'DOWNLOAD_DELAY': 1.25,
    'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101 Firefox/102.0'
})

process.crawl(TheSpider)
process.start()

This is the item:

from scrapy import Item, Field
from itemloaders.processors import Identity, Compose


def all_lower(value):
    return value.lower()


class TheItem(Item):
    title = Field(
        input_processor=Compose(all_lower),
        output_processor=Identity()
    )
    link = Field(
        input_processor=Compose(all_lower),
        output_processor=Identity()
    )
    date = Field(
        input_processor=Compose(all_lower),
        output_processor=Identity()
    )
    category = Field(
        input_processor=Compose(all_lower),
        output_processor=Identity()
    )
    manditory = Field(
        input_processor=Compose(all_lower),
        output_processor=Identity()
    )

This is the output:

    D:\GitFolder\scrapyProjects\TheProject\venv\Scripts\python.exe D:\GitFolder\scrapyProjects\TheProject\TheSpider\TheSpider\spiders\TheSpider.py 
Traceback (most recent call last):
  File "D:\GitFolder\scrapyProjects\TheProject\TheSpider\TheSpider\spiders\TheSpider.py", line 43, in <module>
    process = CrawlerProcess(settings={
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\crawler.py", line 289, in __init__
    super().__init__(settings)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\crawler.py", line 164, in __init__
    settings = Settings(settings)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 454, in __init__
    self.update(values, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 323, in update
    self.set(name, value, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 265, in set
    self.attributes[name].set(value, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 50, in set
    value = BaseSettings(value, priority=priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 86, in __init__
    self.update(values, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 316, in update
    values = json.loads(values)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2032.0_x64__qbz5n2kfra8p0\lib\json\__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2032.0_x64__qbz5n2kfra8p0\lib\json\decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2032.0_x64__qbz5n2kfra8p0\lib\json\decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

Process finished with exit code 1

And if I remove the start_requests() method, I get this output:

    D:\GitFolder\scrapyProjects\TheProject\venv\Scripts\python.exe D:\GitFolder\scrapyProjects\TheProject\TheSpider\TheSpider\spiders\TheSpider.py 
Traceback (most recent call last):
  File "D:\GitFolder\scrapyProjects\TheProject\TheSpider\TheSpider\spiders\TheSpider.py", line 43, in <module>
    process = CrawlerProcess(settings={
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\crawler.py", line 289, in __init__
    super().__init__(settings)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\crawler.py", line 164, in __init__
    settings = Settings(settings)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 454, in __init__
    self.update(values, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 323, in update
    self.set(name, value, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 265, in set
    self.attributes[name].set(value, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 50, in set
    value = BaseSettings(value, priority=priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 86, in __init__
    self.update(values, priority)
  File "D:\GitFolder\scrapyProjects\TheProject\venv\lib\site-packages\scrapy\settings\__init__.py", line 316, in update
    values = json.loads(values)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2032.0_x64__qbz5n2kfra8p0\lib\json\__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2032.0_x64__qbz5n2kfra8p0\lib\json\decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.2032.0_x64__qbz5n2kfra8p0\lib\json\decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

Process finished with exit code 1

Both ultimately end up with the same error.

CodePudding user response：

According to https://docs.scrapy.org/en/latest/topics/feed-exports.html#feeds FEED param should be a dict. Like:

process = CrawlerProcess(settings={
    "FEEDS": {
        "items.json": {"format": "json"},
    },
})