Bump version: 1.2.0 to 1.3.0 (#80)

.circleci/config.yml

@@ -69,14 +69,14 @@ jobs:
             - run:
                 name: Setup DATA_PATH
                 command: |
-                  printf "\nDATA_PATH = '"$DATA_PATH"'\n" >> scrapydweb_settings_v8.py
+                  printf "\nDATA_PATH = '"$DATA_PATH"'\n" >> scrapydweb_settings_v9.py
       - when:
           condition: <<parameters.use-sqlite>>
           steps:
             - run:
                 name: Set DATABASE_URL to sqlite
                 command: |
-                  printf "\nDATABASE_URL = '"$DATABASE_URL"'\n" >> scrapydweb_settings_v8.py
+                  printf "\nDATABASE_URL = '"$DATABASE_URL"'\n" >> scrapydweb_settings_v9.py
       - when:
           condition: <<parameters.use-postgresql>>
           steps:
@@ -91,7 +91,7 @@ jobs:
                 name: Set DATABASE_URL to postgresql
                 command: |
                   # postgres://circleci@127.0.0.1:5432
-                  printf "\nDATABASE_URL = '"$DATABASE_URL"'\n" >> scrapydweb_settings_v8.py
+                  printf "\nDATABASE_URL = '"$DATABASE_URL"'\n" >> scrapydweb_settings_v9.py
       - when:
           condition: <<parameters.use-mysql>>
           steps:
@@ -121,7 +121,7 @@ jobs:
                 name: Set DATABASE_URL to mysql
                 command: |
                   # mysql://user:passw0rd@127.0.0.1:3306
-                  printf "\nDATABASE_URL = '"$DATABASE_URL"'\n" >> scrapydweb_settings_v8.py
+                  printf "\nDATABASE_URL = '"$DATABASE_URL"'\n" >> scrapydweb_settings_v9.py
 
       - run:
           name: Install dependencies
@@ -168,8 +168,8 @@ jobs:
       - run:
           name: Generate report
           command: |
-            touch scrapydweb_settings_v8.py
-            cat scrapydweb_settings_v8.py
+            touch scrapydweb_settings_v9.py
+            cat scrapydweb_settings_v9.py
             echo $DATA_PATH
             echo $DATABASE_URL
             . venv/bin/activate

HISTORY.md

@@ -1,5 +1,20 @@
 Release History
 ===============
+[1.3.0](https://github.com/my8100/scrapydweb/issues?q=is%3Aclosed+milestone%3A1.3.0) (2019-08-04)
+------------------
+- New Features
+  - Add new pages Node Reports and Cluster Reports for aggregating jobs stats [(issue #72)](https://github.com/my8100/scrapydweb/issues/72)
+- Improvements
+  - Adapt to [:link: *LogParser*](https://github.com/my8100/logparser) v0.8.2
+  - Add DATA_PATH option for customizing path to save program data [(issue #40)](https://github.com/my8100/scrapydweb/issues/40)
+  - Add DATABASE_URL option to support MySQL or PostgreSQL backend [(issue #42)](https://github.com/my8100/scrapydweb/issues/42)
+  - Support specify the latest version of Scrapy project in the Run Spider page [(issue #4)](https://github.com/my8100/scrapydweb/issues/4#issuecomment-475145676)
+  - Support specify default values of settings & arguments in the Run Spider page [(issue #55)](https://github.com/my8100/scrapydweb/issues/55)
+- Others
+  - Update config file to scrapydweb_settings_v9.py
+  - Support continuous integration (CI) on [CircleCI](https://circleci.com/)
+
+
 1.2.0 (2019-03-12)
 ------------------
 - New Features

README.md

@@ -66,10 +66,14 @@ and restart Scrapyd to make it visible externally.
 ```bash
 pip install scrapydweb
 ```
-:heavy_exclamation_mark: Note that you may need to execute `pip install -U pip` first in order to get the latest version of scrapydweb, or download the tar.gz file from https://pypi.org/project/scrapydweb/#files and get it installed via `pip install scrapydweb-x.x.x.tar.gz`
+:heavy_exclamation_mark: Note that you may need to execute `python -m pip install --upgrade pip` first in order to get the latest version of scrapydweb, or download the tar.gz file from https://pypi.org/project/scrapydweb/#files and get it installed via `pip install scrapydweb-x.x.x.tar.gz`
 
 - Use git:
 ```bash
+pip install --upgrade git+https://github.com/my8100/scrapydweb.git
+```
+Or:
+```bash
 git clone https://github.com/my8100/scrapydweb.git
 cd scrapydweb
 python setup.py install

README_CN.md

@@ -66,10 +66,14 @@
 ```bash
 pip install scrapydweb
 ```
-:heavy_exclamation_mark: 如果 pip 安装结果不是最新版本的 scrapydweb，请先执行`pip install -U pip`，或者前往 https://pypi.org/project/scrapydweb/#files 下载 tar.gz 文件并执行安装命令 `pip install scrapydweb-x.x.x.tar.gz`
+:heavy_exclamation_mark: 如果 pip 安装结果不是最新版本的 scrapydweb，请先执行`python -m pip install --upgrade pip`，或者前往 https://pypi.org/project/scrapydweb/#files 下载 tar.gz 文件并执行安装命令 `pip install scrapydweb-x.x.x.tar.gz`
 
 - 通过 git:
 ```bash
+pip install --upgrade git+https://github.com/my8100/scrapydweb.git
+```
+或:
+```bash
 git clone https://github.com/my8100/scrapydweb.git
 cd scrapydweb
 python setup.py install

requirements.txt

@@ -3,7 +3,7 @@ APScheduler>=3.5.3
 flask>=1.0.2
 flask-compress>=1.4.0
 Flask-SQLAlchemy>=2.3.2
-logparser==0.8.1
+logparser==0.8.2
 requests>=2.21.0
 setuptools>=40.6.3
 six>=1.12.0

scrapydweb/__init__.py

@@ -215,7 +215,8 @@ def register_view(view, endpoint, url_defaults_list):
     register_view(DeployUploadView, 'deploy.upload', [('deploy/upload', None)])
     register_view(DeployXhrView, 'deploy.xhr', [('deploy/xhr/<eggname>/<project>/<version>', None)])
 
-    from .views.operations.schedule import ScheduleView, ScheduleCheckView, ScheduleRunView, ScheduleXhrView, ScheduleTaskView
+    from .views.operations.schedule import (ScheduleView, ScheduleCheckView, ScheduleRunView,
+                                            ScheduleXhrView, ScheduleTaskView)
     register_view(ScheduleView, 'schedule', [
         ('schedule/<project>/<version>/<spider>', None),
         ('schedule/<project>/<version>', dict(spider=None)),
@@ -271,7 +272,7 @@ def handle_template_context(app):
     STATIC = 'static'
     VERSION = 'v' + __version__.replace('.', '')
     # MUST be commented out for released version
-    VERSION = 'v121dev'
+    # VERSION = 'v131dev'
 
     @app.context_processor
     def inject_variable():

scrapydweb/__version__.py

@@ -1,7 +1,7 @@
 # coding: utf-8
 
 __title__ = 'scrapydweb'
-__version__ = '1.2.0'
+__version__ = '1.3.0'
 __author__ = 'my8100'
 __author_email__ = 'my8100@gmail.com'
 __url__ = 'https://github.com/my8100/scrapydweb'

scrapydweb/default_settings.py

@@ -61,11 +61,14 @@
 # to the Scrapyd server.
 # e.g. '127.0.0.1:6800' or 'localhost:6801', do not forget the port number.
 LOCAL_SCRAPYD_SERVER = ''
+
 # Enter the directory when you run Scrapyd, run the command below
 # to find out where the Scrapy logs are stored:
 # python -c "from os.path import abspath, isdir; from scrapyd.config import Config; path = abspath(Config().get('logs_dir')); print(path); print(isdir(path))"
+# Check out https://scrapyd.readthedocs.io/en/stable/config.html#logs-dir for more info.
 # e.g. 'C:/Users/username/logs' or '/home/username/logs'
 LOCAL_SCRAPYD_LOGS_DIR = ''
+
 # The default is False, set it to True to automatically run LogParser as a subprocess at startup.
 # Note that you can run the LogParser service separately via command 'logparser' as you like.
 # Run 'logparser -h' to find out the config file of LogParser for more advanced settings.

scrapydweb/run.py

@@ -133,7 +133,9 @@ def load_custom_settings(config):
                      "Then add your SCRAPYD_SERVERS in the config file and restart scrapydweb.\n".format(
                       file=SCRAPYDWEB_SETTINGS_PY))
         else:
-            sys.exit("\nThe config file '{file}' has been copied to current working directory.\n"
+            sys.exit("\nATTENTION:\nYou may encounter ERROR if there are any timer tasks added in v1.2.0,\n"
+                     "and you have to restart scrapydweb and manually restart the stopped tasks.\n"
+                     "\nThe config file '{file}' has been copied to current working directory.\n"
                      "Please add your SCRAPYD_SERVERS in the config file and restart scrapydweb.\n".format(
                       file=SCRAPYDWEB_SETTINGS_PY))
 

scrapydweb/templates/scrapydweb/cluster_reports.html

@@ -12,7 +12,11 @@
 {% endblock %}
 
 {% block body %}
-<h2>{{ selected_nodes|length }} Reports of /{{ project }}/{{ spider }}/{{ job }}/</h2>
+<h2>
+  {% if selected_nodes %}<a class="link" target="_blank" href="{{ url_report }}">{% endif %}
+  {{ selected_nodes|length }} Reports of /{{ project }}/{{ spider }}/{{ job }}/
+  {% if selected_nodes %}</a>{% endif %}
+</h2>
 
 <form method="post" enctype="multipart/form-data" hidden></form>
 

scrapydweb/utils/check_app_config.py

@@ -334,7 +334,7 @@ def check_connectivity(server):
         (_group, _ip, _port, _auth) = server
         try:
             url = 'http://%s:%s' % (_ip, _port)
-            r = session.get(url, auth=_auth, timeout=30)
+            r = session.get(url, auth=_auth, timeout=10)
             assert r.status_code == 200, "%s got status_code %s" % (url, r.status_code)
         except Exception as err:
             logger.error(err)

scrapydweb/utils/setup_database.py

@@ -51,6 +51,7 @@ def setup_database(database_url, database_path):
             'jobs': '/'.join([database_url, DB_JOBS])
         }
     else:
+        # db names for backward compatibility
         APSCHEDULER_DATABASE_URI = 'sqlite:///' + '/'.join([database_path, 'apscheduler.db'])
         # http://flask-sqlalchemy.pocoo.org/2.3/binds/#binds
         SQLALCHEMY_DATABASE_URI = 'sqlite:///' + '/'.join([database_path, 'timer_tasks.db'])
@@ -80,7 +81,8 @@ def setup_mysql(username, password, host, port):
     """
     ModuleNotFoundError: No module named 'MySQLdb'
     pip install mysqlclient
-    Python 2: pip install mysqlclient -> MySQLdb/_mysql.c(29) : fatal error C1083: Cannot open include file: 'mysql.h': No such file or directory
+    Python 2: pip install mysqlclient -> MySQLdb/_mysql.c(29) :
+    fatal error C1083: Cannot open include file: 'mysql.h': No such file or directory
     https://stackoverflow.com/questions/51294268/pip-install-mysqlclient-returns-fatal-error-c1083-cannot-open-file-mysql-h
     https://www.lfd.uci.edu/~gohlke/pythonlibs/#mysqlclient
     pip install "path to the downloaded mysqlclient.whl file"
@@ -148,7 +150,8 @@ def setup_postgresql(username, password, host, port):
         # creating-utf-8-database-in-postgresql-on-windows10
 
         # cur.execute("CREATE DATABASE %s ENCODING 'UTF8' LC_COLLATE 'en-US' LC_CTYPE 'en-US'" % dbname)
-        # psycopg2.DataError: new collation (en-US) is incompatible with the collation of the template database (Chinese (Simplified)_People's Republic of China.936)
+        # psycopg2.DataError: new collation (en-US) is incompatible with the collation of the template database
+        # (Chinese (Simplified)_People's Republic of China.936)
         # HINT:  Use the same collation as in the template database, or use template0 as template.
         try:
             cur.execute("CREATE DATABASE %s ENCODING 'UTF8' LC_COLLATE 'en_US.UTF-8' LC_CTYPE 'en_US.UTF-8'" % dbname)

scrapydweb/vars.py

@@ -15,7 +15,7 @@
 
 PYTHON_VERSION = '.'.join([str(n) for n in sys.version_info[:3]])
 PY2 = sys.version_info.major < 3
-SCRAPYDWEB_SETTINGS_PY = 'scrapydweb_settings_v8.py'
+SCRAPYDWEB_SETTINGS_PY = 'scrapydweb_settings_v9.py'
 try:
     custom_settings_module = importlib.import_module(os.path.splitext(SCRAPYDWEB_SETTINGS_PY)[0])
 except ImportError:

scrapydweb/views/api.py

@@ -89,10 +89,10 @@ def handle_result(self):
         elif self.opt == 'liststats':
             if self.js.get('logparser_version') != self.LOGPARSER_VERSION:
                 if self.project and self.version_spider_job:  # 'List Stats' in the Servers page
-                    tip = "'pip install -U logparser' to update LogParser to v%s" % self.LOGPARSER_VERSION
+                    tip = "'pip install --upgrade logparser' to update LogParser to v%s" % self.LOGPARSER_VERSION
                     self.js = dict(status=self.OK, tip=tip)
                 else:  # XMLHttpRequest in the Jobs page; POST in jobs.py
-                    self.js['tip'] = ("'pip install -U logparser' on host '%s' and run command 'logparser' "
+                    self.js['tip'] = ("'pip install --upgrade logparser' on host '%s' and run command 'logparser' "
                                       "to update LogParser to v%s") % (self.SCRAPYD_SERVER, self.LOGPARSER_VERSION)
                     self.js['status'] = self.ERROR
             elif self.project and self.version_spider_job:  # 'List Stats' in the Servers page

scrapydweb/views/dashboard/jobs.py

@@ -367,8 +367,9 @@ def handle_jobs_without_db(self):
             else:
                 if job['finish']:
                     self.finished_jobs.append(job)
-                    job['url_multinode_run'] = url_for('servers', node=self.node, opt='schedule', project=job['project'],
-                                                       version_job=self.DEFAULT_LATEST_VERSION, spider=job['spider'])
+                    job['url_multinode_run'] = url_for('servers', node=self.node, opt='schedule',
+                                                       project=job['project'], version_job=self.DEFAULT_LATEST_VERSION,
+                                                       spider=job['spider'])
                     job['url_schedule'] = url_for('schedule', node=self.node, project=job['project'],
                                                   version=self.DEFAULT_LATEST_VERSION, spider=job['spider'])
                     job['url_start'] = url_for('api', node=self.node, opt='start', project=job['project'],
@@ -384,7 +385,7 @@ def handle_jobs_without_db(self):
                 job['url_stats'] = url_for('log', node=self.node, opt='stats', project=job['project'], ui=self.UI,
                                            spider=job['spider'], job=job['job'], job_finished=job_finished)
                 job['url_clusterreports'] = url_for('clusterreports', node=self.node, project=job['project'],
-                                             spider=job['spider'], job=job['job'])
+                                                    spider=job['spider'], job=job['job'])
                 # <a href='/items/demo/test/2018-10-12_205507.jl'>Items</a>
                 m = re.search(HREF_PATTERN, job['href_items'])
                 if m:

scrapydweb/views/files/log.py

@@ -33,8 +33,8 @@
 job_finished_key_dict = defaultdict(OrderedDict)
 # For /log/report/
 job_finished_report_dict = defaultdict(OrderedDict)
-REPORT_KEYS_SET = set(['from_memory', 'status', 'pages', 'items', 'shutdown_reason', 'finish_reason',
-                       'runtime', 'first_log_time', 'latest_log_time', 'log_categories', 'latest_matches'])
+REPORT_KEYS_SET = {'from_memory', 'status', 'pages', 'items', 'shutdown_reason', 'finish_reason', 'runtime',
+                   'first_log_time', 'latest_log_time', 'log_categories', 'latest_matches'}
 
 
 # http://flask.pocoo.org/docs/1.0/api/#flask.views.View
@@ -110,7 +110,7 @@ def __init__(self):
         self.email_content_kwargs = {}
         self.flag = ''
 
-        self.jobs_to_keep = self.JOBS_FINISHED_JOBS_LIMIT or 1000
+        self.jobs_to_keep = self.JOBS_FINISHED_JOBS_LIMIT or 200
 
     def dispatch_request(self, **kwargs):
         if self.report_logparser:
@@ -205,7 +205,7 @@ def request_stats_by_logparser(self):
                        "Or wait until LogParser parses the log. ") % self.SCRAPYD_SERVER, self.WARN)
             return
         elif js.get('logparser_version') != self.LOGPARSER_VERSION:
-            msg = "'pip install -U logparser' on host '%s' to update LogParser to v%s" % (
+            msg = "'pip install --upgrade logparser' on host '%s' to update LogParser to v%s" % (
                 self.SCRAPYD_SERVER, self.LOGPARSER_VERSION)
             self.logger.warning(msg)
             flash(msg, self.WARN)

scrapydweb/views/operations/execute_task.py

@@ -16,7 +16,7 @@
 EXTRACT_URL_SERVER_PATTERN = re.compile(r'//(.+?:\d+)')
 
 
-class TaskExecuter(object):
+class TaskExecutor(object):
 
     def __init__(self, task_id, task_name, url_scrapydweb, url_schedule_task, url_delete_task_result,
                  auth, selected_nodes):
@@ -159,14 +159,14 @@ def execute_task(task_id):
             username = metadata.get('username', '')
             password = metadata.get('password', '')
             url_delete_task_result = metadata.get('url_delete_task_result', '/1/tasks/xhr/delete/1/1/')
-            task_executer = TaskExecuter(task_id=task_id,
+            task_executor = TaskExecutor(task_id=task_id,
                                          task_name=task.name,
                                          url_scrapydweb=metadata.get('url_scrapydweb', 'http://127.0.0.1:5000'),
                                          url_schedule_task=metadata.get('url_schedule_task', '/1/schedule/task/'),
                                          url_delete_task_result=url_delete_task_result,
                                          auth=(username, password) if username and password else None,
                                          selected_nodes=json.loads(task.selected_nodes))
             try:
-                task_executer.main()
+                task_executor.main()
             except Exception:
                 apscheduler_logger.error(traceback.format_exc())

setup.py

@@ -13,7 +13,7 @@
     exec(f.read(), about)
 
 with io.open("README.md", 'r', encoding='utf-8') as f:
-    long_description = re.sub(r':\w+:\s', '', f.read())  # Remove emojis
+    long_description = re.sub(r':\w+:\s', '', f.read())  # Remove emoji
 
 
 setup(
@@ -37,7 +37,7 @@
         "flask >= 1.0.2",  # May 2, 2018
         "flask-compress >= 1.4.0",  # Jan 5, 2017
         "Flask-SQLAlchemy >= 2.3.2",  # Oct 11, 2017
-        "logparser == 0.8.1",
+        "logparser == 0.8.2",
         "requests >= 2.21.0",  # Dec 10, 2018
         "setuptools >= 40.6.3",  # Dec 11, 2018
         "six >= 1.12.0",  # Dec 10, 2018

tests/test_aa_logparser.py

@@ -128,7 +128,7 @@ def rename(name, restore=False):
     replace_file_content(app.config['DEMO_JSON_PATH'], old, new)
     req(app, client, view='log', kws=kws,
         ins=["Mismatching logparser_version 0.0.0 in local stats",
-             "pip install -U logparser", "Using local logfile:", tab])
+             "pip install --upgrade logparser", "Using local logfile:", tab])
     replace_file_content(app.config['DEMO_JSON_PATH'], new, old)
 
     # delete ScrapydWeb_demo.json in logs

tests/test_reports.py

@@ -28,7 +28,7 @@ def test_cluster_reports(app, client):
                              spider=cst.SPIDER, job=cst.JOBID)
         url_redirect_to_clusterreports = url_for('clusterreports', node=1, project=cst.PROJECT,
                                                  spider=cst.SPIDER, job=cst.JOBID)
-    ins = ['<h2>0 Reports of ////</h2>', '>Select a job</el-button>', url_jobs, 'selected_nodes: [],']
+    ins = ['0 Reports of ////', '>Select a job</el-button>', url_jobs, 'selected_nodes: [],']
     nos = ['>Select nodes</el-button>']
     req(app, client, view='clusterreports', kws=dict(node=1), ins=ins)
 
@@ -37,7 +37,7 @@ def test_cluster_reports(app, client):
         '1': 'on',
         '2': 'on',
     }
-    ins[0] = '<h2>%s Reports of /%s/%s/%s/</h2>' % (len(data), cst.PROJECT, cst.SPIDER, cst.JOBID)
+    ins[0] = '%s Reports of /%s/%s/%s/' % (len(data), cst.PROJECT, cst.SPIDER, cst.JOBID)
     ins[-1] = 'selected_nodes: [1, 2],'
     ins.extend(nos)
     ins.append(url_servers)