我试图根据黄页的类别对其进行剪贴。因此,我从文本文件加载类别并将其输入到start_urls。我在这里面临的问题是为每个类别分别保存输出。以下是我尝试实现的代码:
CATEGORIES = []
with open('Catergories.txt', 'r') as f:
data = f.readlines()
for category in data:
CATEGORIES.append(category.strip())
在settings.py中打开文件并列出要在Spider中访问的列表。
蜘蛛:
# -*- coding: utf-8 -*-
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from ..items import YellowItem
from scrapy.utils.project import get_project_settings
settings = get_project_settings()
class YpSpider(CrawlSpider):
categories = settings.get('CATEGORIES')
name = 'yp'
allowed_domains = ['yellowpages.com']
start_urls = ['https://www.yellowpages.com/search?search_terms={0}&geo_location_terms=New%20York'
'%2C '
'%20NY'.format(*categories)]
rules = (
Rule(LinkExtractor(restrict_xpaths='//a[@class="business-name"]', allow=''), callback='parse_item',
follow=True),
Rule(LinkExtractor(restrict_xpaths='//a[@class="next ajax-page"]', allow=''),
follow=True),
)
def parse_item(self, response):
categories = settings.get('CATEGORIES')
print(categories)
item = YellowItem()
# for data in response.xpath('//section[@class="info"]'):
item['title'] = response.xpath('//h1/text()').extract_first()
item['phone'] = response.xpath('//p[@class="phone"]/text()').extract_first()
item['street_address'] = response.xpath('//h2[@class="address"]/text()').extract_first()
email = response.xpath('//a[@class="email-business"]/@href').extract_first()
try:
item['email'] = email.replace("mailto:", '')
except AttributeError:
pass
item['website'] = response.xpath('//a[@class="primary-btn website-link"]/@href').extract_first()
item['Description'] = response.xpath('//dd[@class="general-info"]/text()').extract_first()
item['Hours'] = response.xpath('//div[@class="open-details"]/descendant-or-self::*/text()[not(ancestor::*['
'@class="hour-category"])]').extract()
item['Other_info'] = response.xpath(
'//dd[@class="other-information"]/descendant-or-self::*/text()').extract()
category_ha = response.xpath('//dd[@class="categories"]/descendant-or-self::*/text()').extract()
item['Categories'] = " ".join(category_ha)
item['Years_in_business'] = response.xpath('//div[@class="number"]/text()').extract_first()
neighborhood = response.xpath('//dd[@class="neighborhoods"]/descendant-or-self::*/text()').extract()
item['neighborhoods'] = ' '.join(neighborhood)
item['other_links'] = response.xpath('//dd[@class="weblinks"]/descendant-or-self::*/text()').extract()
item['category'] = '{0}'.format(*categories)
return item
这是pipelines.py文件:
from scrapy import signals
from scrapy.exporters import CsvItemExporter
from scrapy.utils.project import get_project_settings
settings = get_project_settings()
class YellowPipeline(object):
@classmethod
def from_crawler(cls, crawler):
pipeline = cls()
crawler.signals.connect(pipeline.spider_opened, signals.spider_opened)
crawler.signals.connect(pipeline.spider_closed, signals.spider_closed)
return pipeline
def spider_opened(self, spider):
self.exporters = {}
categories = settings.get('CATEGORIES')
file = open('{0}.csv'.format(*categories), 'w+b')
exporter = CsvItemExporter(file, encoding='cp1252')
exporter.fields_to_export = ['title', 'phone', 'street_address', 'website', 'email', 'Description',
'Hours', 'Other_info', 'Categories', 'Years_in_business', 'neighborhoods',
'other_links']
exporter.start_exporting()
for category in categories:
self.exporters[category] = exporter
def spider_closed(self, spider):
for exporter in iter(self.exporters.items()):
exporter.finish_exporting()
def process_item(self, item, spider):
self.exporters[item['category']].export_item(item)
return item
运行代码后,出现以下错误:
exporter.finish_exporting()
AttributeError: 'tuple' object has no attribute 'finish_exporting'
我需要为每个类别使用单独的csv文件。任何帮助,将不胜感激。
我会在后处理中执行此操作。将所有项目导出到一个带有类别字段的.csv文件。我认为您不是在以正确的方式考虑这个问题,而是让它变得过于复杂。不知道这是否还能工作,但值得一试:)
with open(parent.csv, 'r') as file:
reader = csv.reader(file)
for row in reader:
with open('{}.csv'.format(row[category]), 'a') as f:
writer = csv.writer(f)
writer.writerow(row)