modify scripts
This commit is contained in:
@ -1,3 +1,4 @@
|
||||
from datetime import datetime
|
||||
import scrapy
|
||||
from urllib.parse import urljoin
|
||||
from scrapy_proj.spiders.base_spider import BaseSpider, extract_text_from_element
|
||||
@ -110,7 +111,8 @@ class Sis001Spider(BaseSpider):
|
||||
|
||||
# 判断是否还要翻页,只有满足所有页面的数据,日期均小于开始日期时,停止翻页
|
||||
up_date = parse_date_to_datetime(item['update_date'])
|
||||
if up_date and self.begin and up_date < self.begin :
|
||||
self.logger.debug(f"url: {response.url} update: {up_date}, begin: {self.begin}, now: {datetime.now()}")
|
||||
if up_date and self.begin and (up_date < self.begin or up_date>datetime.now()) :
|
||||
self.logger.debug(f"find early data.")
|
||||
else:
|
||||
need_next = True
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
from datetime import datetime
|
||||
import scrapy
|
||||
from scrapy_proj.spiders.base_spider import BaseSpider, extract_text_from_element
|
||||
from scrapy_proj.items import U001Item
|
||||
@ -11,7 +12,7 @@ class U001Spider(BaseSpider):
|
||||
def __init__(self, debug='False', begin=None, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self.debug = True if (str(debug).lower() == 'true' or str(debug).lower() == '1') else False
|
||||
self.logger.info(f"debug mod: {self.debug}")
|
||||
self.logger.info(f"debug mod: {self.debug}, begin: {begin}")
|
||||
|
||||
self.begin = parse_date_to_datetime(begin) if begin else None
|
||||
|
||||
@ -36,7 +37,8 @@ class U001Spider(BaseSpider):
|
||||
|
||||
# 判断是否还要翻页,只有满足所有页面的数据,日期均小于开始日期时,停止翻页
|
||||
up_date = parse_date_to_datetime(item['update_date'])
|
||||
if up_date and self.begin and up_date < self.begin :
|
||||
self.logger.debug(f"url: {response.url} update: {up_date}, begin: {self.begin}, now: {datetime.now()}")
|
||||
if up_date and self.begin and (up_date < self.begin or up_date>datetime.now()):
|
||||
self.logger.debug(f"find early data.")
|
||||
else:
|
||||
need_next = True
|
||||
|
||||
Reference in New Issue
Block a user