update

scrapyd/Dockerfile

@@ -37,7 +37,6 @@ RUN apt-get update \
     && curl -sSL https://bootstrap.pypa.io/get-pip.py | python \
     && pip install git+https://github.com/scrapy/scrapy.git \
                    git+https://github.com/scrapy/scrapyd.git \
-                   service_identity \
     && curl -sSL https://github.com/scrapy/scrapy/raw/master/extras/scrapy_bash_completion -o /etc/bash_completion.d/scrapy_bash_completion \
     && echo 'source /etc/bash_completion.d/scrapy_bash_completion' >> /root/.bashrc \
     && apt-get remove -y autoconf \

scrapyd/README.md

@@ -1,8 +1,52 @@
 scrapyd
 =======
 
-Dockerfile for building an image that runs [scrapyd][1].  
+Dockerfile for building an image that runs [scrapy][1] and [scrapyd][2].  
+
+Only two latest python packages are installed:
+
+- `scrapy`: git+https://github.com/scrapy/scrapy.git
+- `scrapyd`: git+https://github.com/scrapy/scrapyd.git
 
 Please use this image as base for your own project.
 
-[1]: https://github.com/scrapy/scrapyd
+## run as background-daemon for scrapyd
+
+```
+$ docker run -d --restart always --name scrapyd -p 6800:6800 vimagick/scrapyd
+$ firefox http://localhost:6800
+```
+
+## run as interactive-shell for scrapy
+
+```
+$ cat > stackoverflow_spider.py << _EOF_
+import scrapy
+
+class StackOverflowSpider(scrapy.Spider):
+    name = 'stackoverflow'
+    start_urls = ['http://stackoverflow.com/questions?sort=votes']
+
+    def parse(self, response):
+        for href in response.css('.question-summary h3 a::attr(href)'):
+            full_url = response.urljoin(href.extract())
+            yield scrapy.Request(full_url, callback=self.parse_question)
+
+    def parse_question(self, response):
+        yield {
+            'title': response.css('h1 a::text').extract()[0],
+            'votes': response.css('.question .vote-count-post::text').extract()[0],
+            'body': response.css('.question .post-text').extract()[0],
+            'tags': response.css('.question .post-tag::text').extract(),
+            'link': response.url,
+        }
+_EOF_
+
+$ docker run --rm --name scrapy -v `pwd`:/code -w /code vimagick/scrapyd bash
+>>> scrapy runspider stackoverflow_spider.py -o top-stackoverflow-questions.json
+>>> cat top-stackoverflow-questions.json
+>>> exit
+```
+
+[1]: https://github.com/scrapy/scrapy
+[2]: https://github.com/scrapy/scrapyd