def delete_proxy(ip, port):
""" 删除数据库中的代理
:param ip: ip
:param port: 端口
"""
if ip != "" and port != "":
db = DBSession()
db.query(Proxy).filter(Proxy.ip == ip).filter(Proxy.port == port).delete()
try:
db.commit()
return True
except exc.SQLAlchemyError, e:
logging.info("Delete Proxy Error:", format(e))
return False
def process_item(self, item, spider):
# try:
# con = MySQLdb.connect(**config.db_config)
# cur = con.cursor()
# sql = "INSERT INTO leiju_proxy (ip,port,proto,checked_at,created_at) VALUES (%s,%s,%s,%s,%s)"
# parmam = [(item['ip'], item['port'], 'http', int(time.time()), int(time.time()))]
# cur.executemany(sql, parmam)
# con.commit()
# con.close()
# # return item
# except Exception, e:
# logging.info("SaveError: %s:%s %s" % (item['ip'], item['port'], format(e)))
# raise DropItem("SaveError: %s:%s %s" % (item['ip'], item['port'], format(e)))
db = DBSession()
md5 = hashlib.md5()
md5.update(item['ip'] + "." + item['port'])
haship = md5.hexdigest()
proxy = Proxy(haship=haship,
ip=item['ip'],
port=item['port'],
create_time=int(time.time()))
db.add(proxy)
try:
db.commit()
except exc.SQLAlchemyError, e:
raise DropItem("SaveError: %s:%s %s" %
(item['ip'], item['port'], format(e)))
def process_item(self, item, spider):
# try:
# con = MySQLdb.connect(**config.db_config)
# cur = con.cursor()
# sql = "INSERT INTO leiju_proxy (ip,port,proto,checked_at,created_at) VALUES (%s,%s,%s,%s,%s)"
# parmam = [(item['ip'], item['port'], 'http', int(time.time()), int(time.time()))]
# cur.executemany(sql, parmam)
# con.commit()
# con.close()
# # return item
# except Exception, e:
# logging.info("SaveError: %s:%s %s" % (item['ip'], item['port'], format(e)))
# raise DropItem("SaveError: %s:%s %s" % (item['ip'], item['port'], format(e)))
db = DBSession()
md5 = hashlib.md5()
md5.update(item['ip'] + "." + item['port'])
haship = md5.hexdigest()
proxy = Proxy(haship=haship, ip=item['ip'], port=item['port'], create_time=int(time.time()))
db.add(proxy)
try:
db.commit()
except exc.SQLAlchemyError, e:
raise DropItem("SaveError: %s:%s %s" % (item['ip'], item['port'], format(e)))
def delete_proxy(ip, port):
""" 删除数据库中的代理
:param ip: ip
:param port: 端口
"""
if ip != "" and port != "":
db = DBSession()
db.query(Proxy).filter(Proxy.ip == ip).filter(
Proxy.port == port).delete()
try:
db.commit()
return True
except exc.SQLAlchemyError, e:
logging.info("Delete Proxy Error:", format(e))
return False
def process_item(self, item, spider):
db = DBSession()
redis = confRedis
rule_id = spider.rule_id
url = item['url']
md5 = hashlib.md5()
md5.update(url)
urlmd5 = md5.hexdigest()
site_name = utils.get_site(item['url'])
# site_name = spider.rule['allow_domains']
html_title = item['html_title']
# html_body = item['html_body']
save_path = utils.md5dir(item['url'])
save_time = int(time.time())
title = item['title'] if 'title' in item else ""
body = item['body'] if 'body' in item else ""
thumb = item['thumb'] if 'thumb' in item else ""
img_list = item['img_list'] if 'img_list' in item else ""
# TODO 这里使用一个分析方法,分析抓取到数据的发布时间,然后转换成时间戳
publish_time = utils.smart2date(item['publish_time']) if 'publish_time' in item else ""
source_site = item['source_site'] if 'source_site' in item else ""
flag = default_page_flag
page = Page(rule_id=rule_id, url=item['url'], urlmd5=urlmd5, site_name=site_name, html_title=html_title,
save_path=save_path,
save_time=save_time, title=title,
thumb=thumb, img_list=img_list,
body=body, publish_time=publish_time,
source_site=source_site, flag=flag)
has = db.query(Page).filter(Page.urlmd5 == urlmd5).first()
if has:
page = Page(rule_id=rule_id, url=item['url'], site_name=site_name, html_title=html_title,
save_path=save_path,
save_time=save_time, title=title,
thumb=thumb, img_list=img_list,
body=body, publish_time=publish_time,
source_site=source_site, flag=flag)
db.add(page)
try:
db.commit()
utils.save_file('%s/%s' % (html_path, save_path), item['html_body'])
redis.set('url:%s' % url, 1)
except exc.SQLAlchemyError, e:
raise DropItem("SaveDbError: %s,%s" % (url, format(e)))
def get_proxy_list():
""" 获取代理列表"""
db = DBSession()
proxy_list = db.query(Proxy).all()
db.close()
return proxy_list
# python
# -*- coding: utf-8 -*-
# from sqlalchemy import exc
from conf.config import DBSession
from util import WebProxy as webProxy
from model.Proxy import Proxy
db = DBSession()
ips = db.query(Proxy).all()
for item in ips:
ret = webProxy.check_proxy(item.ip, item.port)
if not ret:
webProxy.delete_proxy(item.ip, item.port)
# save_path=TEXT(stored=True)
)
if not os.path.exists(search_path):
os.mkdir(search_path)
ix = create_in(search_path, schema)
writer = ix.writer()
# fromtimestamp int->time
# time = 0
# datetime.datetime.fromtimestamp(time)
# strptime string->time
# format = '%Y-%m-%d %H:%M:%S' str = '2015-10-27 15:09:38'
# datetime.datetime.strptime(str,format)
timeformat = '%Y-%m-%d %H:%M:%S'
db = DBSession()
""" 过滤条件参照该文件最下面的增量索引的方案 """
# 新增数据
# sql = text('insert into users (u_name, u_password) values (:name, :password)')
# data = db.execute(sql, {'name': 'nate1', 'password': password})
# 删除数据
# sql = text('delete from users where u_id = :id')
# data = session.execute(sql, {'id': last_id})
# sql = text('select * from users')
# data = session.execute(sql)
# 查询SQL版本
sql = text('select * from Page where id < :id')
pageList = db.execute(sql, {'id': 20})
# 查询ORM版本
# pageList = db.query(Page).filter(Page.id < 20).all()
def process_item(self, item, spider):
db = DBSession()
redis = confRedis
rule_id = spider.rule_id
url = item['url']
md5 = hashlib.md5()
md5.update(url)
urlmd5 = md5.hexdigest()
site_name = utils.get_site(item['url'])
# site_name = spider.rule['allow_domains']
html_title = item['html_title']
# html_body = item['html_body']
save_path = utils.md5dir(item['url'])
save_time = int(time.time())
title = item['title'] if 'title' in item else ""
body = item['body'] if 'body' in item else ""
thumb = item['thumb'] if 'thumb' in item else ""
img_list = item['img_list'] if 'img_list' in item else ""
# TODO 这里使用一个分析方法,分析抓取到数据的发布时间,然后转换成时间戳
publish_time = utils.smart2date(
item['publish_time']) if 'publish_time' in item else ""
source_site = item['source_site'] if 'source_site' in item else ""
flag = default_page_flag
page = Page(rule_id=rule_id,
url=item['url'],
urlmd5=urlmd5,
site_name=site_name,
html_title=html_title,
save_path=save_path,
save_time=save_time,
title=title,
thumb=thumb,
img_list=img_list,
body=body,
publish_time=publish_time,
source_site=source_site,
flag=flag)
has = db.query(Page).filter(Page.urlmd5 == urlmd5).first()
if has:
page = Page(rule_id=rule_id,
url=item['url'],
site_name=site_name,
html_title=html_title,
save_path=save_path,
save_time=save_time,
title=title,
thumb=thumb,
img_list=img_list,
body=body,
publish_time=publish_time,
source_site=source_site,
flag=flag)
db.add(page)
try:
db.commit()
utils.save_file('%s/%s' % (html_path, save_path),
item['html_body'])
redis.set('url:%s' % url, 1)
except exc.SQLAlchemyError, e:
raise DropItem("SaveDbError: %s,%s" % (url, format(e)))
def get_proxy_list():
""" 获取代理列表"""
db = DBSession()
proxy_list = db.query(Proxy).all()
db.close()
return proxy_list
# python
# -*- coding: utf-8 -*-
from conf.config import DBSession, log_format, log_file, log_path, log_open, img_save_path
from model.Rule import Rule
from spiders.RuleSpider import RuleSpider
from scrapy.crawler import CrawlerProcess
from scrapy.settings import Settings
from scrapy.utils.log import configure_logging
import logging
from datetime import datetime
import os
db = DBSession()
def run_spider():
settings = Settings()
settings.set("COOKIES_ENABLES", False) # 禁止cookies追踪
settings.set(
"ITEM_PIPELINES",
{
'pipelines.ImgPipline': 150, # 保存图片到本地
# 'pipelines.CoverImagesPipeline': 150, # 保存图片到七牛云
'pipelines.SaveCommonPipline': 200, # 保存数据库
# 'pipelines.FilterUrlPipline': 300,
})
settings.set(
"DOWNLOADER_MIDDLEWARES",
{
