RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5070 from ric2b/patch-1

This commit is contained in:
Andrey Rahmatullin 2021-04-15 14:50:59 +05:00 committed by GitHub
parent 06f3d12c12 8603f9d7a5
commit 5b78a64fca
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docs/topics/practices.rst
View File

@ -119,6 +119,7 @@ Here is an example that runs multiple spiders simultaneously:
import scrapy
from scrapy.crawler import CrawlerProcess
from scrapy.utils.project import get_project_settings
class MySpider1(scrapy.Spider):
# Your first spider definition
@ -128,7 +129,8 @@ Here is an example that runs multiple spiders simultaneously:
# Your second spider definition
...
process = CrawlerProcess()
settings = get_project_settings()
process = CrawlerProcess(settings)
process.crawl(MySpider1)
process.crawl(MySpider2)
process.start() # the script will block here until all crawling jobs are finished
@ -141,6 +143,7 @@ Same example using :class:`~scrapy.crawler.CrawlerRunner`:
from twisted.internet import reactor
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
from scrapy.utils.project import get_project_settings
class MySpider1(scrapy.Spider):
# Your first spider definition
@ -151,7 +154,8 @@ Same example using :class:`~scrapy.crawler.CrawlerRunner`:
...
configure_logging()
runner = CrawlerRunner()
settings = get_project_settings()
runner = CrawlerRunner(settings)
runner.crawl(MySpider1)
runner.crawl(MySpider2)
d = runner.join()
@ -166,6 +170,7 @@ Same example but running the spiders sequentially by chaining the deferreds:
from twisted.internet import reactor, defer
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
from scrapy.utils.project import get_project_settings
class MySpider1(scrapy.Spider):
# Your first spider definition
@ -176,7 +181,8 @@ Same example but running the spiders sequentially by chaining the deferreds:
...
configure_logging()
runner = CrawlerRunner()
settings = get_project_settings()
runner = CrawlerRunner(settings)
@defer.inlineCallbacks
def crawl():