I have made a spider to get reviews from a page like this here using scrapy. I want product reviews only till a certain date(2nd July 2016 in this case). I want to close my spider as soon as the review date goes earlier than the given date and return the items list.
Spider is working well but my problem is that i am not able to close my spider if the condition is met..if i raise an exception, spider closes without returning anything.
Please suggest the best way to close the spider manually. Here is my code:
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy import Selector
from tars.items import FlipkartProductReviewsItem
import re as r
import unicodedata
from datetime import datetime
class Freviewspider(CrawlSpider):
name = "frs"
allowed_domains = ["flipkart.com"]
def __init__(self, *args, **kwargs):
super(Freviewspider, self).__init__(*args, **kwargs)
self.start_urls = [kwargs.get('start_url')]
rules = (
Rule(LinkExtractor(allow=(), restrict_xpaths=('//a[@class="nav_bar_next_prev"]')), callback="parse_start_url", follow= True),
)
def parse_start_url(self, response):
hxs = Selector(response)
titles = hxs.xpath('//div[@class="fclear fk-review fk-position-relative line "]')
items = []
for i in titles:
item = FlipkartProductReviewsItem()
#x-paths:
title_xpath = "div[2]/div[1]/strong/text()"
review_xpath = "div[2]/p/span/text()"
date_xpath = "div[1]/div[3]/text()"
#field-values-extraction:
item["date"] = (''.join(i.xpath(date_xpath).extract())).replace('
', '')
item["title"] = (''.join(i.xpath(title_xpath).extract())).replace('
', '')
review_list = i.xpath(review_xpath).extract()
temp_list = []
for element in review_list:
temp_list.append(element.replace('
', '').replace('
', ''))
item["review"] = ' '.join(temp_list)
xxx = datetime.strptime(item["date"], '%d %b %Y ')
comp_date = datetime.strptime('02 Jul 2016 ', '%d %b %Y ')
if xxx>comp_date:
items.append(item)
else:
break
return(items)
See Question&Answers more detail:
os 与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…