Merge pull request #4552 from jay24rajput/common_commands

Code sharing between crawl and runspider command
This commit is contained in:
Andrey Rahmatullin 2020-06-03 12:06:12 +05:00 committed by GitHub
commit 63929e75e3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 29 additions and 45 deletions

View File

@ -5,7 +5,7 @@ import os
from optparse import OptionGroup
from twisted.python import failure
from scrapy.utils.conf import arglist_to_dict
from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli
from scrapy.exceptions import UsageError
@ -104,3 +104,27 @@ class ScrapyCommand:
Entry point for running commands
"""
raise NotImplementedError
class BaseRunSpiderCommand(ScrapyCommand):
"""
Common class used to share functionality between the crawl and runspider commands
"""
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
help="set spider argument (may be repeated)")
parser.add_option("-o", "--output", metavar="FILE", action="append",
help="dump scraped items into FILE (use - for stdout)")
parser.add_option("-t", "--output-format", metavar="FORMAT",
help="format to use for dumping items with -o")
def process_options(self, args, opts):
ScrapyCommand.process_options(self, args, opts)
try:
opts.spargs = arglist_to_dict(opts.spargs)
except ValueError:
raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)
if opts.output:
feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format)
self.settings.set('FEEDS', feeds, priority='cmdline')

View File

@ -1,9 +1,8 @@
from scrapy.commands import ScrapyCommand
from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli
from scrapy.commands import BaseRunSpiderCommand
from scrapy.exceptions import UsageError
class Command(ScrapyCommand):
class Command(BaseRunSpiderCommand):
requires_project = True
@ -13,25 +12,6 @@ class Command(ScrapyCommand):
def short_desc(self):
return "Run a spider"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
help="set spider argument (may be repeated)")
parser.add_option("-o", "--output", metavar="FILE", action="append",
help="dump scraped items into FILE (use - for stdout)")
parser.add_option("-t", "--output-format", metavar="FORMAT",
help="format to use for dumping items with -o")
def process_options(self, args, opts):
ScrapyCommand.process_options(self, args, opts)
try:
opts.spargs = arglist_to_dict(opts.spargs)
except ValueError:
raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)
if opts.output:
feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format)
self.settings.set('FEEDS', feeds, priority='cmdline')
def run(self, args, opts):
if len(args) < 1:
raise UsageError()

View File

@ -3,9 +3,8 @@ import os
from importlib import import_module
from scrapy.utils.spider import iter_spider_classes
from scrapy.commands import ScrapyCommand
from scrapy.exceptions import UsageError
from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli
from scrapy.commands import BaseRunSpiderCommand
def _import_file(filepath):
@ -24,7 +23,7 @@ def _import_file(filepath):
return module
class Command(ScrapyCommand):
class Command(BaseRunSpiderCommand):
requires_project = False
default_settings = {'SPIDER_LOADER_WARN_ONLY': True}
@ -38,25 +37,6 @@ class Command(ScrapyCommand):
def long_desc(self):
return "Run the spider defined in the given file"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
help="set spider argument (may be repeated)")
parser.add_option("-o", "--output", metavar="FILE", action="append",
help="dump scraped items into FILE (use - for stdout)")
parser.add_option("-t", "--output-format", metavar="FORMAT",
help="format to use for dumping items with -o")
def process_options(self, args, opts):
ScrapyCommand.process_options(self, args, opts)
try:
opts.spargs = arglist_to_dict(opts.spargs)
except ValueError:
raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)
if opts.output:
feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format)
self.settings.set('FEEDS', feeds, priority='cmdline')
def run(self, args, opts):
if len(args) != 1:
raise UsageError()