My scraper works fine when I run it from the command line, but when I try to run it from within a python script (with the method outlined here using Twisted) it does not output the two CSV files that it normally does. I have a pipeline that creates and populates these files, one of them using CsvItemExporter() and the other using writeCsvFile(). Here is the code:
class CsvExportPipeline(object):
def __init__(self):
self.files = {}
@classmethod
def from_crawler(cls, crawler):
pipeline = cls()
crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
return pipeline
def spider_opened(self, spider):
nodes = open('%s_nodes.csv' % spider.name, 'w+b')
self.files[spider] = nodes
self.exporter1 = CsvItemExporter(nodes, fields_to_export=['url','name','screenshot'])
self.exporter1.start_exporting()
self.edges = []
self.edges.append(['Source','Target','Type','ID','Label','Weight'])
self.num = 1
def spider_closed(self, spider):
self.exporter1.finish_exporting()
file = self.files.pop(spider)
file.close()
writeCsvFile(getcwd()+r'\edges.csv', self.edges)
def process_item(self, item, spider):
self.exporter1.export_item(item)
for url in item['links']:
self.edges.append([item['url'],url,'Directed',self.num,'',1])
self.num += 1
return item
Here is my file structure:
SiteCrawler/ # the CSVs are normally created in this folder
runspider.py # this is the script that runs the scraper
scrapy.cfg
SiteCrawler/
__init__.py
items.py
pipelines.py
screenshooter.py
settings.py
spiders/
__init__.py
myfuncs.py
sitecrawler_spider.py
The scraper appears to function normally in all other ways. The output at the end in the command line suggests that the expected number of pages were crawled and the spider appears to have finished normally. I am not getting any error messages.
---- EDIT : ----
Inserting print statements and syntax errors into the pipeline has no effect, so it appears that the pipeline is being ignored. Why might this be?
Here is the code for the script that runs the scraper (runspider.py):
from twisted.internet import reactor
from scrapy import log, signals
from scrapy.crawler import Crawler
from scrapy.settings import Settings
from scrapy.xlib.pydispatch import dispatcher
import logging
from SiteCrawler.spiders.sitecrawler_spider import MySpider
def stop_reactor():
reactor.stop()
dispatcher.connect(stop_reactor, signal=signals.spider_closed)
spider = MySpider()
crawler = Crawler(Settings())
crawler.configure()
crawler.crawl(spider)
crawler.start()
log.start(loglevel=logging.DEBUG)
log.msg('Running reactor...')
reactor.run() # the script will block here until the spider is closed
log.msg('Reactor stopped.')
