Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Fix permission handling on project generation from template files

Adrián Chaves79b4dfc53e43
diff --git a/scrapy/commands/startproject.py b/scrapy/commands/startproject.py
index 852281959..e702d7cdc 100644
--- a/scrapy/commands/startproject.py
+++ b/scrapy/commands/startproject.py
@@ -1,10 +1,10 @@
import re
import os
-import stat
import string
from importlib import import_module
from os.path import join, exists, abspath
from shutil import ignore_patterns, move, copy2, copystat
+from stat import S_IWUSR as OWNER_WRITE_PERMISSION
import scrapy
from scrapy.commands import ScrapyCommand
@@ -78,30 +78,12 @@ class Command(ScrapyCommand):
self._copytree(srcname, dstname)
else:
copy2(srcname, dstname)
- copystat(src, dst)
- self._set_rw_permissions(dst)
+ current_permissions = os.stat(dstname).st_mode
+ os.chmod(dstname, current_permissions | OWNER_WRITE_PERMISSION)
- def _set_rw_permissions(self, path):
- """
- Sets permissions of a directory tree to +rw and +rwx for folders.
- This is necessary if the start template files come without write
- permissions.
- """
- mode_rw = (stat.S_IRUSR
- | stat.S_IWUSR
- | stat.S_IRGRP
- | stat.S_IROTH)
-
- mode_x = (stat.S_IXUSR
- | stat.S_IXGRP
- | stat.S_IXOTH)
-
- os.chmod(path, mode_rw | mode_x)
- for root, dirs, files in os.walk(path):
- for dir in dirs:
- os.chmod(join(root, dir), mode_rw | mode_x)
- for file in files:
- os.chmod(join(root, file), mode_rw)
+ copystat(src, dst)
+ current_permissions = os.stat(dst).st_mode
+ os.chmod(dst, current_permissions | OWNER_WRITE_PERMISSION)
def run(self, args, opts):
if len(args) not in (1, 2):
diff --git a/tests/sample_data/read_only_templates/project/module/__init__.py b/tests/sample_data/read_only_templates/project/module/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/tests/sample_data/read_only_templates/project/module/items.py.tmpl b/tests/sample_data/read_only_templates/project/module/items.py.tmpl
new file mode 100644
index 000000000..88a18331c
--- /dev/null
+++ b/tests/sample_data/read_only_templates/project/module/items.py.tmpl
@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ${ProjectName}Item(scrapy.Item):
+ # define the fields for your item here like:
+ # name = scrapy.Field()
+ pass
diff --git a/tests/sample_data/read_only_templates/project/module/middlewares.py.tmpl b/tests/sample_data/read_only_templates/project/module/middlewares.py.tmpl
new file mode 100644
index 000000000..bd09890fe
--- /dev/null
+++ b/tests/sample_data/read_only_templates/project/module/middlewares.py.tmpl
@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class ${ProjectName}SpiderMiddleware:
+ # Not all methods need to be defined. If a method is not defined,
+ # scrapy acts as if the spider middleware does not modify the
+ # passed objects.
+
+ @classmethod
+ def from_crawler(cls, crawler):
+ # This method is used by Scrapy to create your spiders.
+ s = cls()
+ crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+ return s
+
+ def process_spider_input(self, response, spider):
+ # Called for each response that goes through the spider
+ # middleware and into the spider.
+
+ # Should return None or raise an exception.
+ return None
+
+ def process_spider_output(self, response, result, spider):
+ # Called with the results returned from the Spider, after
+ # it has processed the response.
+
+ # Must return an iterable of Request, or item objects.
+ for i in result:
+ yield i
+
+ def process_spider_exception(self, response, exception, spider):
+ # Called when a spider or process_spider_input() method
+ # (from other spider middleware) raises an exception.
+
+ # Should return either None or an iterable of Request or item objects.
+ pass
+
+ def process_start_requests(self, start_requests, spider):
+ # Called with the start requests of the spider, and works
+ # similarly to the process_spider_output() method, except
+ # that it doesn’t have a response associated.
+
+ # Must return only requests (not items).
+ for r in start_requests:
+ yield r
+
+ def spider_opened(self, spider):
+ spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class ${ProjectName}DownloaderMiddleware:
+ # Not all methods need to be defined. If a method is not defined,
+ # scrapy acts as if the downloader middleware does not modify the
+ # passed objects.
+
+ @classmethod
+ def from_crawler(cls, crawler):
+ # This method is used by Scrapy to create your spiders.
+ s = cls()
+ crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+ return s
+
+ def process_request(self, request, spider):
+ # Called for each request that goes through the downloader
+ # middleware.
+
+ # Must either:
+ # - return None: continue processing this request
+ # - or return a Response object
+ # - or return a Request object
+ # - or raise IgnoreRequest: process_exception() methods of
+ # installed downloader middleware will be called
+ return None
+
+ def process_response(self, request, response, spider):
+ # Called with the response returned from the downloader.
+
+ # Must either;
+ # - return a Response object
+ # - return a Request object
+ # - or raise IgnoreRequest
+ return response
+
+ def process_exception(self, request, exception, spider):
+ # Called when a download handler or a process_request()
+ # (from other downloader middleware) raises an exception.
+
+ # Must either:
+ # - return None: continue processing this exception
+ # - return a Response object: stops process_exception() chain
+ # - return a Request object: stops process_exception() chain
+ pass
+
+ def spider_opened(self, spider):
+ spider.logger.info('Spider opened: %s' % spider.name)
diff --git a/tests/sample_data/read_only_templates/project/module/pipelines.py.tmpl b/tests/sample_data/read_only_templates/project/module/pipelines.py.tmpl
new file mode 100644
index 000000000..e845f43e9
--- /dev/null
+++ b/tests/sample_data/read_only_templates/project/module/pipelines.py.tmpl
@@ -0,0 +1,13 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class ${ProjectName}Pipeline:
+ def process_item(self, item, spider):
+ return item
diff --git a/tests/sample_data/read_only_templates/project/module/settings.py.tmpl b/tests/sample_data/read_only_templates/project/module/settings.py.tmpl
new file mode 100644
index 000000000..a414b5fde
--- /dev/null
+++ b/tests/sample_data/read_only_templates/project/module/settings.py.tmpl
@@ -0,0 +1,88 @@
+# Scrapy settings for $project_name project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+# https://docs.scrapy.org/en/latest/topics/settings.html
+# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = '$project_name'
+
+SPIDER_MODULES = ['$project_name.spiders']
+NEWSPIDER_MODULE = '$project_name.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = '$project_name (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+# 'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+# '$project_name.middlewares.${ProjectName}SpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+# '$project_name.middlewares.${ProjectName}DownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+# 'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+# '$project_name.pipelines.${ProjectName}Pipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
diff --git a/tests/sample_data/read_only_templates/project/module/spiders/__init__.py b/tests/sample_data/read_only_templates/project/module/spiders/__init__.py
new file mode 100644
index 000000000..ebd689ac5
--- /dev/null
+++ b/tests/sample_data/read_only_templates/project/module/spiders/__init__.py
@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.
diff --git a/tests/sample_data/read_only_templates/project/scrapy.cfg b/tests/sample_data/read_only_templates/project/scrapy.cfg
new file mode 100644
index 000000000..1daeaa541
--- /dev/null
+++ b/tests/sample_data/read_only_templates/project/scrapy.cfg
@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = ${project_name}.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = ${project_name}
diff --git a/tests/sample_data/read_only_templates/spiders/basic.tmpl b/tests/sample_data/read_only_templates/spiders/basic.tmpl
new file mode 100644
index 000000000..e9112bc95
--- /dev/null
+++ b/tests/sample_data/read_only_templates/spiders/basic.tmpl
@@ -0,0 +1,10 @@
+import scrapy
+
+
+class $classname(scrapy.Spider):
+ name = '$name'
+ allowed_domains = ['$domain']
+ start_urls = ['http://$domain/']
+
+ def parse(self, response):
+ pass
diff --git a/tests/sample_data/read_only_templates/spiders/crawl.tmpl b/tests/sample_data/read_only_templates/spiders/crawl.tmpl
new file mode 100644
index 000000000..356496487
--- /dev/null
+++ b/tests/sample_data/read_only_templates/spiders/crawl.tmpl
@@ -0,0 +1,20 @@
+import scrapy
+from scrapy.linkextractors import LinkExtractor
+from scrapy.spiders import CrawlSpider, Rule
+
+
+class $classname(CrawlSpider):
+ name = '$name'
+ allowed_domains = ['$domain']
+ start_urls = ['http://$domain/']
+
+ rules = (
+ Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True),
+ )
+
+ def parse_item(self, response):
+ item = {}
+ #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
+ #item['name'] = response.xpath('//div[@id="name"]').get()
+ #item['description'] = response.xpath('//div[@id="description"]').get()
+ return item
diff --git a/tests/sample_data/read_only_templates/spiders/csvfeed.tmpl b/tests/sample_data/read_only_templates/spiders/csvfeed.tmpl
new file mode 100644
index 000000000..cbcbe9e2c
--- /dev/null
+++ b/tests/sample_data/read_only_templates/spiders/csvfeed.tmpl
@@ -0,0 +1,20 @@
+from scrapy.spiders import CSVFeedSpider
+
+
+class $classname(CSVFeedSpider):
+ name = '$name'
+ allowed_domains = ['$domain']
+ start_urls = ['http://$domain/feed.csv']
+ # headers = ['id', 'name', 'description', 'image_link']
+ # delimiter = '\t'
+
+ # Do any adaptations you need here
+ #def adapt_response(self, response):
+ # return response
+
+ def parse_row(self, response, row):
+ i = {}
+ #i['url'] = row['url']
+ #i['name'] = row['name']
+ #i['description'] = row['description']
+ return i
diff --git a/tests/sample_data/read_only_templates/spiders/xmlfeed.tmpl b/tests/sample_data/read_only_templates/spiders/xmlfeed.tmpl
new file mode 100644
index 000000000..5aa2aa8b0
--- /dev/null
+++ b/tests/sample_data/read_only_templates/spiders/xmlfeed.tmpl
@@ -0,0 +1,16 @@
+from scrapy.spiders import XMLFeedSpider
+
+
+class $classname(XMLFeedSpider):
+ name = '$name'
+ allowed_domains = ['$domain']
+ start_urls = ['http://$domain/feed.xml']
+ iterator = 'iternodes' # you can change this; see the docs
+ itertag = 'item' # change it accordingly
+
+ def parse_node(self, response, selector):
+ item = {}
+ #item['url'] = selector.select('url').get()
+ #item['name'] = selector.select('name').get()
+ #item['description'] = selector.select('description').get()
+ return item
diff --git a/tests/test_commands.py b/tests/test_commands.py
index 24a341759..8336c8759 100644
--- a/tests/test_commands.py
+++ b/tests/test_commands.py
@@ -6,7 +6,9 @@ import subprocess
import sys
import tempfile
from contextlib import contextmanager
+from itertools import chain
from os.path import exists, join, abspath
+from pathlib import Path
from shutil import rmtree, copytree
from tempfile import mkdtemp
from threading import Timer
@@ -15,6 +17,7 @@ from twisted.trial import unittest
import scrapy
from scrapy.commands import ScrapyCommand
+from scrapy.commands.startproject import IGNORE
from scrapy.settings import Settings
from scrapy.utils.python import to_unicode
from scrapy.utils.test import get_testenv
@@ -119,8 +122,34 @@ class StartprojectTest(ProjectTest):
self.assertEqual(2, self.call('startproject', self.project_name, project_dir, 'another_params'))
+def get_permissions_dict(path, renamings=None, ignore=None):
+ renamings = renamings or tuple()
+ permissions_dict = {
+ '.': os.stat(path).st_mode,
+ }
+ for root, dirs, files in os.walk(path):
+ nodes = list(chain(dirs, files))
+ if ignore:
+ ignored_names = ignore(root, nodes)
+ nodes = [node for node in nodes
+ if node not in ignored_names]
+ for node in nodes:
+ absolute_path = os.path.join(root, node)
+ relative_path = os.path.relpath(absolute_path, path)
+ for search_string, replacement in renamings:
+ relative_path = relative_path.replace(
+ search_string,
+ replacement
+ )
+ permissions = os.stat(absolute_path).st_mode
+ permissions_dict[relative_path] = permissions
+ return permissions_dict
+
+
class StartprojectTemplatesTest(ProjectTest):
+ maxDiff = None
+
def setUp(self):
super(StartprojectTemplatesTest, self).setUp()
self.tmpl = join(self.temp_path, 'templates')
@@ -139,6 +168,141 @@ class StartprojectTemplatesTest(ProjectTest):
self.assertIn(self.tmpl_proj, out)
assert exists(join(self.proj_path, 'root_template'))
+ def test_startproject_permissions_from_writable(self):
+ """Check that generated files have the right permissions when the
+ template folder has the same permissions as in the project, i.e.
+ everything is writable."""
+ scrapy_path = scrapy.__path__[0]
+ templates_dir = os.path.join(scrapy_path, 'templates', 'project')
+ project_name = 'startproject1'
+ renamings = (
+ ('module', project_name),
+ ('.tmpl', ''),
+ )
+ expected_permissions = get_permissions_dict(
+ templates_dir,
+ renamings,
+ IGNORE,
+ )
+
+ destination = mkdtemp()
+ process = subprocess.Popen(
+ (
+ sys.executable,
+ '-m',
+ 'scrapy.cmdline',
+ 'startproject',
+ project_name,
+ ),
+ cwd=destination,
+ env=self.env,
+ )
+ process.wait()
+
+ project_dir = os.path.join(destination, project_name)
+ actual_permissions = get_permissions_dict(project_dir)
+
+ self.assertEqual(actual_permissions, expected_permissions)
+
+ def test_startproject_permissions_from_read_only(self):
+ """Check that generated files have the right permissions when the
+ template folder has been made read-only, which is something that some
+ systems do.
+
+ See https://github.com/scrapy/scrapy/pull/4604
+ """
+ scrapy_path = scrapy.__path__[0]
+ templates_dir = os.path.join(scrapy_path, 'templates', 'project')
+ project_name = 'startproject2'
+ renamings = (
+ ('module', project_name),
+ ('.tmpl', ''),
+ )
+ expected_permissions = get_permissions_dict(
+ templates_dir,
+ renamings,
+ IGNORE,
+ )
+
+ tests_path = os.path.dirname(__file__)
+ read_only_templates_dir = os.path.join(
+ tests_path, 'sample_data', 'read_only_templates'
+ )
+ destination = mkdtemp()
+ process = subprocess.Popen(
+ (
+ sys.executable,
+ '-m',
+ 'scrapy.cmdline',
+ 'startproject',
+ project_name,
+ '--set',
+ 'TEMPLATES_DIR={}'.format(read_only_templates_dir),
+ ),
+ cwd=destination,
+ env=self.env,
+ )
+ process.wait()
+
+ project_dir = os.path.join(destination, project_name)
+ actual_permissions = get_permissions_dict(project_dir)
+
+ self.assertEqual(actual_permissions, expected_permissions)
+
+ def test_startproject_permissions_unchanged_in_destination(self):
+ """Check that pre-existing folders and files in the destination folder
+ do not see their permissions modified."""
+ scrapy_path = scrapy.__path__[0]
+ templates_dir = os.path.join(scrapy_path, 'templates', 'project')
+ project_name = 'startproject3'
+ renamings = (
+ ('module', project_name),
+ ('.tmpl', ''),
+ )
+ expected_permissions = get_permissions_dict(
+ templates_dir,
+ renamings,
+ IGNORE,
+ )
+
+ destination = mkdtemp()
+ project_dir = os.path.join(destination, project_name)
+
+ existing_nodes = {
+ oct(permissions)[2:] + extension: permissions
+ for extension in ('', '.d')
+ for permissions in (
+ 0o444, 0o555, 0o644, 0o666, 0o755, 0o777,
+ )
+ }
+ os.mkdir(project_dir)
+ project_dir_path = Path(project_dir)
+ for node, permissions in existing_nodes.items():
+ path = project_dir_path / node
+ if node.endswith('.d'):
+ path.mkdir(mode=permissions)
+ else:
+ path.touch(mode=permissions)
+ expected_permissions[node] = path.stat().st_mode
+
+ process = subprocess.Popen(
+ (
+ sys.executable,
+ '-m',
+ 'scrapy.cmdline',
+ 'startproject',
+ project_name,
+ '.',
+ ),
+ cwd=project_dir,
+ env=self.env,
+ )
+ process.wait()
+
+ actual_permissions = get_permissions_dict(project_dir)
+
+ self.assertEqual(actual_permissions, expected_permissions)
+
class CommandTest(ProjectTest):