为什么Python Scrapy库类不是'；不执行

我正试图在IBMCloud上使用Scrapy作为一个函数。我的

\uuuu main\uuuu.py

如下所示：

import scrapy
from scrapy.crawler import CrawlerProcess

class AutoscoutListSpider(scrapy.Spider):
    name = "vehicles list"

    def __init__(self, params, *args, **kwargs):
        super(AutoscoutListSpider, self).__init__(*args, **kwargs)
        make = params.get("make", None)
        model = params.get("model", None)
        mileage = params.get("mileage", None)

        init_url = "https://www.autoscout24.be/nl/resultaten?sort=standard&desc=0&ustate=N%2CU&size=20&page=1&cy=B&mmvmd0={0}&mmvmk0={1}&kmto={2}&atype=C&".format(
            model, make, mileage)
        self.start_urls = [init_url]

    def parse(self, response):
        # Get total result on list load
        init_total_results = int(response.css('.cl-filters-summary-counter::text').extract_first().replace('.', ''))
        if init_total_results > 400:
            yield {"message": "There are MORE then 400 results"}
        else:
            yield {"message": "There are LESS then 400 results"}


def main(params):
    process = CrawlerProcess()
    try:
        process.crawl(AutoscoutListSpider, params)
        process.start()
        return {"Success ": "The crawler (make: {0}, model: {1}, mileage: {2}) is successfully executed.".format(
            params['make'], params['model'], params['mileage'])}
    except Exception as e:
        return {"Error ": e, "params ": params}

{"Success ": "The crawler (make: 9, model: 1624, mileage: 2500) is successfully executed."}

main({"make":"9", "model":"1624", "mileage":"2500"})

添加此功能的整个过程如下：

import scrapy
from scrapy.crawler import CrawlerProcess

class AutoscoutListSpider(scrapy.Spider):
    name = "vehicles list"

    def __init__(self, params, *args, **kwargs):
        super(AutoscoutListSpider, self).__init__(*args, **kwargs)
        make = params.get("make", None)
        model = params.get("model", None)
        mileage = params.get("mileage", None)

        init_url = "https://www.autoscout24.be/nl/resultaten?sort=standard&desc=0&ustate=N%2CU&size=20&page=1&cy=B&mmvmd0={0}&mmvmk0={1}&kmto={2}&atype=C&".format(
            model, make, mileage)
        self.start_urls = [init_url]

    def parse(self, response):
        # Get total result on list load
        init_total_results = int(response.css('.cl-filters-summary-counter::text').extract_first().replace('.', ''))
        if init_total_results > 400:
            yield {"message": "There are MORE then 400 results"}
        else:
            yield {"message": "There are LESS then 400 results"}


def main(params):
    process = CrawlerProcess()
    try:
        process.crawl(AutoscoutListSpider, params)
        process.start()
        return {"Success ": "The crawler (make: {0}, model: {1}, mileage: {2}) is successfully executed.".format(
            params['make'], params['model'], params['mileage'])}
    except Exception as e:
        return {"Error ": e, "params ": params}

{"Success ": "The crawler (make: 9, model: 1624, mileage: 2500) is successfully executed."}

main({"make":"9", "model":"1624", "mileage":"2500"})

zip-r ascrawler.zip\uuuu main\uuuupy common.py

//因此我创建了一个zip文件来上传它。（还有一个common.py文件。为了简单起见，我从这里删除了它。）

ibmcloud wsk action create ascrawler--kind python:3 ascrawler.zip

//创建函数并将其添加到云中

ibmcloud wsk action invoke--blocking--result ascrawler--param make 9--param model 1624--param miliety 2500

//使用参数调用函数

执行第三步后，我得到如下结果：

import scrapy
from scrapy.crawler import CrawlerProcess

class AutoscoutListSpider(scrapy.Spider):
    name = "vehicles list"

    def __init__(self, params, *args, **kwargs):
        super(AutoscoutListSpider, self).__init__(*args, **kwargs)
        make = params.get("make", None)
        model = params.get("model", None)
        mileage = params.get("mileage", None)

        init_url = "https://www.autoscout24.be/nl/resultaten?sort=standard&desc=0&ustate=N%2CU&size=20&page=1&cy=B&mmvmd0={0}&mmvmk0={1}&kmto={2}&atype=C&".format(
            model, make, mileage)
        self.start_urls = [init_url]

    def parse(self, response):
        # Get total result on list load
        init_total_results = int(response.css('.cl-filters-summary-counter::text').extract_first().replace('.', ''))
        if init_total_results > 400:
            yield {"message": "There are MORE then 400 results"}
        else:
            yield {"message": "There are LESS then 400 results"}


def main(params):
    process = CrawlerProcess()
    try:
        process.crawl(AutoscoutListSpider, params)
        process.start()
        return {"Success ": "The crawler (make: {0}, model: {1}, mileage: {2}) is successfully executed.".format(
            params['make'], params['model'], params['mileage'])}
    except Exception as e:
        return {"Error ": e, "params ": params}

{"Success ": "The crawler (make: 9, model: 1624, mileage: 2500) is successfully executed."}

main({"make":"9", "model":"1624", "mileage":"2500"})

因此，我没有得到任何错误，但它根本没有出现在

AutoscoutListSpider

类中。为什么?

它还应该返回

{“message”：“有超过400个结果”}

。有什么想法吗

当我从python控制台运行它时，如下所示：

import scrapy
from scrapy.crawler import CrawlerProcess

class AutoscoutListSpider(scrapy.Spider):
    name = "vehicles list"

    def __init__(self, params, *args, **kwargs):
        super(AutoscoutListSpider, self).__init__(*args, **kwargs)
        make = params.get("make", None)
        model = params.get("model", None)
        mileage = params.get("mileage", None)

        init_url = "https://www.autoscout24.be/nl/resultaten?sort=standard&desc=0&ustate=N%2CU&size=20&page=1&cy=B&mmvmd0={0}&mmvmk0={1}&kmto={2}&atype=C&".format(
            model, make, mileage)
        self.start_urls = [init_url]

    def parse(self, response):
        # Get total result on list load
        init_total_results = int(response.css('.cl-filters-summary-counter::text').extract_first().replace('.', ''))
        if init_total_results > 400:
            yield {"message": "There are MORE then 400 results"}
        else:
            yield {"message": "There are LESS then 400 results"}


def main(params):
    process = CrawlerProcess()
    try:
        process.crawl(AutoscoutListSpider, params)
        process.start()
        return {"Success ": "The crawler (make: {0}, model: {1}, mileage: {2}) is successfully executed.".format(
            params['make'], params['model'], params['mileage'])}
    except Exception as e:
        return {"Error ": e, "params ": params}

{"Success ": "The crawler (make: 9, model: 1624, mileage: 2500) is successfully executed."}

main({"make":"9", "model":"1624", "mileage":"2500"})

它返回正确的结果：

{"message": "There are MORE then 400 results"}
{"Success ": "The crawler (make: 9, model: 1624, mileage: 2500) is successfully executed."}

{“message”：“有超过400个结果”}

在调用的激活日志中可用，而不是操作结果

运行

ibmcloud wsk action invoke

命令后，检索上一次调用的激活标识符

$ ibmcloud wsk activation list
activations
d13bd19b196d420dbbd19b196dc20d59 ascrawler
...

$ ibmcloud wsk activation logs d13bd19b196d420dbbd19b196dc20d59 | grep LESS
2018-06-29T08:27:11.094873294Z stderr: {'message': 'There are LESS then 400 results'}

然后可以使用此激活标识从调用期间写入的stdout和stderr中检索所有控制台日志

$ ibmcloud wsk activation list
activations
d13bd19b196d420dbbd19b196dc20d59 ascrawler
...

$ ibmcloud wsk activation logs d13bd19b196d420dbbd19b196dc20d59 | grep LESS
2018-06-29T08:27:11.094873294Z stderr: {'message': 'There are LESS then 400 results'}

---

谢谢你详细的评论，我明天会看的。@JamesThomas好的。谢谢好消息，一切正常！这些信息被写入控制台日志，而不是从函数返回。你知道为什么这不起作用吗

zip-r ascrawler.zip-venv/bin/activate\u this.py-venv/lib/python3.6/site-packages/raven-venv/lib/python3.6/site-packages/raven-6.9.0.dist-info\u\u main\u.py common.py db.py

？我想使用raven捕获错误，我确实喜欢您的教程，但我得到一个错误

“error”：“该操作没有返回字典。”

。在日志中，“，”2018-07-04T12:55:56.590718898Z标准偏差：来自raven导入客户端“，”2018-07-04T12:55:56.590724452Z标准偏差：模块未找到错误：没有名为“raven”的模块