')
-
-
-def run_app():
- # create folder if it does not exist
- if not os.path.exists(PROJECT_LOGS_FOLDER):
- os.makedirs(PROJECT_LOGS_FOLDER)
-
- # run app instance
- app.run(host=FLASK_HOST, port=FLASK_PORT)
-
-
-def run_flower():
- p = subprocess.Popen(['celery', 'flower', '-b', BROKER_URL], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
- for line in iter(p.stdout.readline, 'b'):
- if line.decode('utf-8') != '':
- other.info(line.decode('utf-8'))
-
-
-def run_worker():
- if sys.platform == 'windows':
- celery_app.start(argv=['tasks', 'worker', '-P', 'eventlet', '-E', '-l', 'INFO'])
- else:
- celery_app.start(argv=['tasks', 'worker', '-E', '-l', 'INFO'])
-
-
-def run_scheduler():
- scheduler.run()
-
-
-@click.command()
-@click.argument('action', type=click.Choice([ActionType.APP,
- ActionType.FLOWER,
- ActionType.WORKER,
- ActionType.SCHEDULER,
- ActionType.RUN_ALL]))
-def main(action):
- if action == ActionType.APP:
- run_app()
- elif action == ActionType.FLOWER:
- run_flower()
- elif action == ActionType.WORKER:
- run_worker()
- elif action == ActionType.SCHEDULER:
- run_scheduler()
- elif action == ActionType.RUN_ALL:
- p_flower = Process(target=run_flower)
- p_flower.start()
- p_app = Process(target=run_app)
- p_app.start()
- p_worker = Process(target=run_worker)
- p_worker.start()
- p_scheduler = Process(target=run_scheduler)
- p_scheduler.start()
-
-
-if __name__ == '__main__':
- main()
diff --git a/crawlab/model/__init__.py b/crawlab/model/__init__.py
deleted file mode 100644
index e69de29b..00000000
diff --git a/crawlab/model/base.py b/crawlab/model/base.py
deleted file mode 100644
index 253cc063..00000000
--- a/crawlab/model/base.py
+++ /dev/null
@@ -1,6 +0,0 @@
-from mongoengine import *
-import datetime
-
-
-class BaseModel(Document):
- create_ts = DateTimeField(default=datetime.datetime.utcnow)
diff --git a/crawlab/model/deploy.py b/crawlab/model/deploy.py
deleted file mode 100644
index 2d21c6fc..00000000
--- a/crawlab/model/deploy.py
+++ /dev/null
@@ -1,10 +0,0 @@
-from mongoengine import *
-
-from model.base import BaseModel
-
-
-class Deploy(BaseModel):
- _id = ObjectIdField()
- spider_id = ObjectIdField()
- version = IntField()
- node_id = ObjectIdField()
diff --git a/crawlab/model/node.py b/crawlab/model/node.py
deleted file mode 100644
index 4b9b4910..00000000
--- a/crawlab/model/node.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from mongoengine import *
-
-from model.base import BaseModel
-
-
-class Node(BaseModel):
- _id = ObjectIdField()
- ip = StringField()
- port = IntField()
- name = StringField()
- description = StringField()
- status = IntField()
diff --git a/crawlab/model/spider.py b/crawlab/model/spider.py
deleted file mode 100644
index eee86711..00000000
--- a/crawlab/model/spider.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from mongoengine import *
-
-from model.base import BaseModel
-
-
-class Spider(BaseModel):
- _id = ObjectIdField()
- name = StringField()
- cmd = StringField()
- src = StringField()
- type = IntField()
- lang = IntField()
diff --git a/crawlab/model/task.py b/crawlab/model/task.py
deleted file mode 100644
index 9f934eb1..00000000
--- a/crawlab/model/task.py
+++ /dev/null
@@ -1,9 +0,0 @@
-from mongoengine import *
-
-from model.base import BaseModel
-
-
-class Task(BaseModel):
- _id = ObjectIdField()
- deploy_id = ObjectIdField()
- file_path = StringField()
diff --git a/crawlab/requirements.txt b/crawlab/requirements.txt
index 8b13446c..0a1b7f13 100644
--- a/crawlab/requirements.txt
+++ b/crawlab/requirements.txt
@@ -57,10 +57,8 @@ python-dateutil==2.8.0
pytz==2018.9
queuelib==1.5.0
redis==3.2.1
-redisbeat==1.1.4
requests==2.21.0
Scrapy==1.6.0
-selenium==3.141.0
service-identity==18.1.0
six==1.12.0
soupsieve==1.9.1
diff --git a/crawlab/routes/spiders.py b/crawlab/routes/spiders.py
index 5fabde73..758cf29c 100644
--- a/crawlab/routes/spiders.py
+++ b/crawlab/routes/spiders.py
@@ -463,9 +463,8 @@ class SpiderApi(BaseApi):
detail_fields = json.loads(args.detail_fields)
db_manager.update_one(col_name='spiders', id=id, values={'detail_fields': detail_fields})
- def preview_crawl(self, id: str):
- spider = db_manager.get(col_name='spiders', id=id)
-
+ @staticmethod
+ def _get_html(spider) -> etree.Element:
if spider['type'] != SpiderType.CONFIGURABLE:
return {
'status': 'ok',
@@ -497,6 +496,26 @@ class SpiderApi(BaseApi):
# get html parse tree
sel = etree.HTML(r.content)
+ return sel
+
+ @staticmethod
+ def _get_text_child_tags(sel):
+ tags = []
+ for tag in sel.iter():
+ if tag.text is not None:
+ tags.append(tag)
+ return tags
+
+ def preview_crawl(self, id: str):
+ spider = db_manager.get(col_name='spiders', id=id)
+
+ # get html parse tree
+ sel = self._get_html(spider)
+
+ # when error happens, return
+ if type(sel) == type(tuple):
+ return sel
+
# parse fields
if spider['crawl_type'] == CrawlType.LIST:
if spider.get('item_selector') is None:
@@ -513,6 +532,7 @@ class SpiderApi(BaseApi):
}
elif spider['crawl_type'] == CrawlType.DETAIL:
+ # TODO: 详情页预览
pass
elif spider['crawl_type'] == CrawlType.LIST_DETAIL:
@@ -534,6 +554,54 @@ class SpiderApi(BaseApi):
'items': data
}
+ def extract_fields(self, id: str):
+ """
+ Extract list fields from a web page
+ :param id:
+ :return:
+ """
+ spider = db_manager.get(col_name='spiders', id=id)
+
+ # get html parse tree
+ sel = self._get_html(spider)
+
+ # when error happens, return
+ if type(sel) == type(tuple):
+ return sel
+
+ list_tag_list = []
+ threshold = 10
+ # iterate all child nodes in a top-down direction
+ for tag in sel.iter():
+ # get child tags
+ child_tags = tag.getchildren()
+
+ if len(child_tags) < threshold:
+ # if number of child tags is below threshold, skip
+ continue
+ else:
+ # have one or more child tags
+ child_tags_set = set(map(lambda x: x.tag, child_tags))
+
+ # if there are more than 1 tag names, skip
+ if len(child_tags_set) > 1:
+ continue
+
+ # add as list tag
+ list_tag_list.append(tag)
+
+ # find the list tag with the most child text tags
+ _tag_list = []
+ _max_tag = None
+ _max_num = 0
+ for tag in list_tag_list:
+ _child_text_tags = self._get_text_child_tags(tag[0])
+ if len(_child_text_tags) > _max_num:
+ _max_tag = tag
+ _max_num = len(_child_text_tags)
+
+ # TODO: extract list fields
+
class SpiderImportApi(Resource):
__doc__ = """
diff --git a/crawlab/setup.py b/crawlab/setup.py
deleted file mode 100644
index 22cda1de..00000000
--- a/crawlab/setup.py
+++ /dev/null
@@ -1,24 +0,0 @@
-from setuptools import setup, find_packages
-
-with open("README.md", "r") as fh:
- long_description = fh.read()
-
-with open('requirements.txt') as f:
- requirements = [l for l in f.read().splitlines() if l]
-
-setup(
- name='crawlab-server',
- version='0.0.1',
- url='https://github.com/tikazyq/crawlab',
- install_requires=requirements,
- license='BSD',
- author='Marvin Zhang',
- author_email='tikazyq@163.com',
- description='Celery-based web crawler admin platform for managing distributed web spiders regardless of languages and frameworks.',
- long_description=long_description,
- long_description_content_type="text/markdown",
- download_url="https://github.com/tikazyq/crawlab/archive/master.zip",
- packages=find_packages(),
- keywords=['celery', 'python', 'webcrawler', 'crawl', 'scrapy', 'admin'],
- zip_safe=True,
-)
diff --git a/frontend/src/components/Config/ConfigList.vue b/frontend/src/components/Config/ConfigList.vue
index 6c47570a..908f2c9a 100644
--- a/frontend/src/components/Config/ConfigList.vue
+++ b/frontend/src/components/Config/ConfigList.vue
@@ -79,6 +79,7 @@
{{$t('Run')}}
+ {{$t('Extract Fields')}}
{{$t('Preview')}}
{{$t('Save')}}
@@ -126,6 +127,7 @@ export default {
{ value: 'detail', label: 'Detail Only' },
{ value: 'list-detail', label: 'List + Detail' }
],
+ extractFieldsLoading: false,
previewLoading: false,
saveLoading: false,
dialogVisible: false
@@ -210,6 +212,8 @@ export default {
this.$message.success(this.$t(`Spider task has been scheduled`))
})
})
+ },
+ onExtractFields () {
}
},
created () {
diff --git a/frontend/src/i18n/zh.js b/frontend/src/i18n/zh.js
index e6db4795..9af096c9 100644
--- a/frontend/src/i18n/zh.js
+++ b/frontend/src/i18n/zh.js
@@ -48,13 +48,14 @@ export default {
Submit: '提交',
'Import Spiders': '导入爬虫',
'Deploy All': '部署所有爬虫',
- Refresh: '刷新',
- View: '查看',
- Edit: '编辑',
- Remove: '删除',
- Confirm: '确认',
- Stop: '停止',
- Preview: '预览',
+ 'Refresh': '刷新',
+ 'View': '查看',
+ 'Edit': '编辑',
+ 'Remove': '删除',
+ 'Confirm': '确认',
+ 'Stop': '停止',
+ 'Preview': '预览',
+ 'Extract Fields': '提取字段',
// 主页
'Total Tasks': '总任务数',
+