class ServiceFactory(factory.django.DjangoModelFactory):
class Meta:
model = Service
title = factory.LazyAttribute(lambda x: faker.sentence(nb_words=3))
description = factory.LazyAttribute(lambda x: faker.sentence(nb_words=20))
author = factory.Iterator(User.objects.all())
category = factory.Iterator(Category.objects.all())
date = factory.Sequence(
lambda n: datetime.datetime.now() + datetime.timedelta(days=n))
seeds_price = factory.Faker('pyint')
photos = factory.RelatedFactory(ServicePhotoFactory, 'service')
def seed_comments():
comments_count = db.session.query(func.count(Comment.id)).scalar()
comments_to_seed = 31
comments_to_seed -= comments_count
sys.stdout.write('[+] Seeding %d comments\n' % comments_to_seed)
comments = []
user_ids = [user[0] for user in User.query.with_entities(User.id).all()]
article_ids = [
article[0] for article in Article.query.with_entities(Article.id)
]
# equivalent:
# user_ids = [user[0] for user in db.session.query(User.id).all()]
# article_ids = [article[0] for article in db.session.query(Article.id).all()]
for i in range(comments_count, comments_to_seed):
user_id = random.choice(user_ids)
article_id = random.choice(article_ids)
comments.append(
Comment(article_id=article_id,
user_id=user_id,
content=faker.sentence()))
db.session.add_all(comments)
db.session.commit()
def seed_products():
products_count = Product.objects.count()
products_to_seed = 35
sys.stdout.write('[+] Seeding %d products\n' % (products_to_seed - products_count))
dir = os.path.join(os.getcwd(), 'static', 'images', 'products')
if not os.path.exists(dir):
os.makedirs(dir)
for i in range(products_count, products_to_seed):
name = faker.sentence()
# slug = faker.slug()
# description = faker.paragraph(nb_sentences=3, variable_nb_sentences=10)
description = faker.text()
tags = Tag.objects.get_random_tag()
categories = Category.objects.gent_random_category()
price = round(random.uniform(150, 3000), 2)
start_date = datetime.date(year=2016, month=1, day=1)
random_date = faker.date_between(start_date=start_date, end_date='+4y')
publish_on = random_date
# publish_on = faker.date_time_between('-3y', '+1y')
product = Product.objects.create(name=name, description=description, price=price,
publish_on=publish_on, stock=faker.random_int(min=0, max=400))
product.tags.add(tags)
product.categories.add(categories)
file_name = "".join(random.choice(ascii_lowercase) for i in range(16))
file_path = os.path.join(dir, file_name)
ProductImage.objects.create(file_name=file_name, original_name='adults.png',
file_length=faker.random.randint(400, 10000),
product=product,
file_path=file_path.replace(os.getcwd(), '').replace('\\', '/'))
def issue_factory():
return {
"title": faker.sentence(),
"body": faker.text(),
"milestone": random.randint(1, 5),
"labels": faker.words(),
"assignees": [faker.user_name() for _ in range(3)]
}
class SourceFactory(DjangoModelFactory):
name = factory.Sequence(lambda x: '{}{}'.format(faker.name(), x))
long_title = factory.Sequence(lambda x: '{}{}'.format(faker.sentence(), x))
icon = factory.SelfAttribute('name')
user = factory.SubFactory(ShareUserFactory, source=None)
class Meta:
model = models.Source
def seed_comments():
comments_count = Comment.objects.count()
comments_to_seed = 31
sys.stdout.write('[+] Seeding %d comments\n' %
(comments_to_seed - comments_count))
for i in range(comments_count, comments_to_seed):
if Comment.objects.count() > 1 and faker.boolean():
Comment.objects.create(
article=Article.objects.order_by('?').first(),
user=AppUser.objects.order_by('?').first(),
content=faker.sentence())
def seed_replies():
replies_count = Comment.objects.exclude(
parent_comment__isnull=True).count()
replies_to_seed = 33
sys.stdout.write('[+] Seeding %d replies\n' %
(replies_to_seed - replies_count))
for i in range(replies_count, replies_to_seed):
Comment.objects.create(
article=Article.objects.order_by('?').first(),
user=AppUser.objects.order_by('?').first(),
content=faker.sentence(),
parent_comment=Comment.objects.order_by('?').first())
def seed_comments():
comments_count = Comment.objects.count()
comments_to_seed = 31
sys.stdout.write('[+] Seeding %d comments\n' % (comments_to_seed - comments_count))
if bool(random.getrandbits(1)):
rating = faker.random_int(min=1, max=5)
else:
rating = None
for i in range(comments_count, comments_to_seed):
Comment.objects.create(content=faker.sentence(), user_id=AppUser.objects.order_by('?').only('id').first().id,
rating=rating,
product=Product.objects.order_by('?').only('id').first())
def seed_articles():
roles = db.session.query(Role.id).filter(
or_(Role.name == 'ROLE_ADMIN', Role.name == 'ROLE_AUTHOR')).all()
# Not working roles = db.session.query(Role.id).filter(Role.name == v for v in ('ROLE_ADMIN', 'ROLE_AUTHOR')).all()
roles = [role[0] for role in roles]
articles_count = db.session.query(func.count(Article.id)).all()[0][0]
articles_to_seed = 23
articles_to_seed -= articles_count
sys.stdout.write('[+] Seeding %d articles\n' % articles_to_seed)
author_admin_ids = [
user[0] for user in db.session.query(User.id).filter(
User.roles.any(UserRole.role_id.in_(roles))).all()
]
tag_ids = [tag[0] for tag in db.session.query(Tag.id).all()]
category_ids = [
category[0] for category in db.session.query(Category.id).all()
]
for i in range(articles_count, articles_to_seed):
title = faker.sentence()
description = '\n'.join(faker.sentences(2))
body = faker.text()
user_id = random.choice(author_admin_ids)
start_date = datetime.date(year=2017, month=1, day=1)
random_date = faker.date_between(start_date=start_date, end_date='+4y')
publish_on = random_date
a = Article(title=title,
body=body,
description=description,
user_id=user_id,
publish_on=publish_on)
a.tags.append(db.session.query(Tag).order_by(func.random()).first())
for i in range(0, random.randint(1, 2)):
a.tags.append(random.choice(tags))
for i in range(0, random.randint(1, 2)):
a.categories.append(random.choice(categories))
db.session.add(a)
db.session.commit()
def seed_articles():
articles_count = Article.objects.count()
articles_to_seed = 23
sys.stdout.write('[+] Seeding %d articles\n' %
(articles_to_seed - articles_count))
for i in range(articles_count, articles_to_seed):
title = faker.sentence()
description = '\n'.join(faker.sentences(2))
body = faker.text()
user = AppUser.objects.order_by('?').first()
tag = Tag.objects.get_random_tag()
category = Category.objects.get_random_category()
start_date = datetime.date(year=2017, month=1, day=1)
random_date = faker.date_between(start_date=start_date, end_date='+4y')
publish_on = random_date
a = Article.objects.create(title=title,
body=body,
description=description,
user=user,
publish_on=publish_on)
a.tags.add(tag)
a.categories.add(category)
# add_all 一次性添加多个对象
session.add_all(faker_users)
# 生成 5 个分类
faker_categories = [Category(name=faker.word()) for i in range(5)]
session.add_all(faker_categories)
# 生成２０个标签
faker_tags = [Tag(name=faker.word()) for i in range(20)]
session.add_all(faker_tags)
# 生成 100 篇文章
for i in range(100):
article = Article(
# sentence() 生成一句话作为标题
title=faker.sentence(),
# 文章内容为随机生成的 10-20句话
content=' '.join(faker.sentences(nb=random.randint(10, 20))),
# 从生成的用户中随机取一个作为作者
author=random.choice(faker_users),
# 从生成的分类中随机取一个作为分类
category=random.choice(faker_categories)
)
# 从生成的标签中随机取 2-5 个作为分类，注意 sample() 函数的用法
for tag in random.sample(faker_tags, random.randint(2, 5)):
article.tags.append(tag)
session.add(article)
session.commit()
<<<<<<< HEAD
=======
class SchoolFactory(DjangoModelFactory):
class Meta:
model = School
name = lazy_attribute(lambda x: faker.sentence(nb_words=4))
def run_more():
faker = Faker('zh-CN')
driver = webdriver.Firefox()
driver.set_page_load_timeout(60)
segmentfaulturs = [
'https://segmentfault.com/companies?page=' + str(i) for i in range(7)
]
for segmentfaulturl in segmentfaulturls:
driver.get(segmentfaulturl)
time.sleep(2)
html = driver.page_source
dom_tree = etree.HTML(html)
# 获取公司的链接
company_urls = dom_tree.xpath(
'//div[@class="row"]/div[@class="media"]/div[@class="col-md-9"]/div[@class="media-body"]/h4[@id="media-heading"]/a[1]/@href'
)
# 获取公司的名称
company_names = dom_tree.xpath(
'//div[@class="row"]/div[@class="media"]/div[@class="col-md-9"]/div[@class="media-body"]/h4[@id="media-heading"]/a/text()'
)
# 获取公司图片的url
company_logos = dom_tree.xpath(
'//div[@class="row"]/div[@class="media"]/div[@class="col-md-9"]/div[@class="pull-left"]/div[@class="img-warp"]/a[@class="company-logo"]/@style'
)
# 获取公司网站
company_websites = dom_tree.xpath(
'//div[@class="row"]/div[@class="media"]/div[@class="col-md-9"]/div[@class="media-body"]/a[@class="company-site"]/@href'
)
# 获取公司一句话介绍
company_onewords = dom_tree.xpath(
'//div[@class="row"]/div[@class="media"]/div[@class="col-md-9"]/div[@class="media-body"]/p[@class="company-desc"]/text()'
)
for company_name in company_names:
print(company_name)
for company_website in company_websites:
print(company_website)
for company_logo in company_logos:
print(company_logo[company_log.rfind('(') +
1:company_logo.rfind(')') - 1])
for company_oneword in company_onewords:
print(company_oneword)
for company_url in company_urls:
company_url = 'https://segmentfault.com' + company_url
print(company_url)
# 获取当前窗口句柄
now_handle = driver.current_window_handle
i = 0
for company_url in company_urls:
name = company_names[i]
email = faker.email()
password = '******'
logo_img = company_logos[i][company_logos[i].rfind('(') +
1:company_logos[i].rfind(')') - 1]
if User.query.filter_by(name=name).first():
# 如果企业存在就不存入数据库
i += 1
print('重复')
continue
# 把用户加入数据库
user = User(name=name,
email=email,
password=password,
logo_img=logo_img,
role=20)
db.session.add(user)
user = User.query.filter_by(name=name).first()
oneword = faker.sentence(nb_words=25)
print(name)
print(logo_img)
print(website)
print(oneword)
description = faker.sentence(nb_words=50)
# 把公司信息加入数据库
company = Company(user=user,
website=website,
oneword=oneword,
description=description)
db.session.add(company)
# 给公司家入职位信息
num = User.query.filter_by(name=name).first().id
ran = random.randint(10, 100)
for j in range(random.randint(10, 20)):
job = Job(name=faker.job(),
wage=str(ran) + 'K - ' + str(ran + 10) + 'K',
location=faker.province(),
company=Company.query.filter_by(user_id=num).first(),
description=faker.sentence(nb_words=25),
requirement=faker.sentence(nb_words=20))
db.session.add(job)
i += 1
driver.close()
# 向数据库提交
try:
db.session.commit()
except Exception as e:
print(e)
db.session.rollback()
Article.tags.get_through_model(), Category, Tag
])
faker = Factory.create()
faker_users = [
User.create(
username=faker.name(),
password=faker.word(),
email=faker.email(),
) for i in range(10)
]
faker_categories = [Category.create(name=faker.word()) for i in range(5)]
faker_tags = [Tag.create(name=faker.word()) for i in range(20)]
for i in range(100):
article = Article(title=faker.sentence(),
content=' '.join(
faker.sentences(nb=random.randint(10, 20))),
author=random.choice(faker_users),
category=random.choice(faker_categories))
article.save()
for tag in random.sample(faker_tags, random.randint(2, 5)):
article.tags.add(tag)
article.save()
uid = str(uuid.uuid4())
lv = random.randint(1, 10)
if lv <= 4:
level = "debug"
elif lv <= 8:
level = "info"
elif lv <= 9:
level = "warning"
else:
level = "error"
log_item = {
"@timestamp":
str(datetime.datetime.utcnow() + datetime.timedelta(hours=8)),
"message":
faker.sentence(nb_words=9),
"muid":
uid,
"level":
level
}
log = json.dumps(log_item)
print(log)
fl = random.randint(1, 4)
if fl == 1:
filename = "/usr/log/xmppclient-a79874f161b7.log"
elif fl == 2:
filename = "/usr/log/querier-a79874f161b7.log"
elif fl == 3:
filename = "/usr/log/callback-a79874f161b7.log"
# -*- coding: utf-8 -*-
# @Time : 2018/12/3 3:19 PM
# @Author : Jax.Li
# @FileName: loggenerater.py
# @Software: PyCharm
# @Blog ：https://blog.jaxli.com
import faker
import datetime
import time
if __name__ == '__main__':
faker = faker.Faker()
# while True:
for index in range(10):
log = "{} INFO {}\n".format(str(datetime.datetime.now()), faker.sentence(nb_words=9))
print(log)
time.sleep(2)
with open("/usr/log/python.log", "a") as file:
file.write(log)