阅读了几个小时的解决方案后，我仍然找不到问题的答案。 我正在尝试抓取超市网页，我认为错误出在解析函数中。如果有人可以帮助我，请。
import scrapy
from bs4 import BeautifulSoup
import re
from fakesupermarketPrueba.items import fakesupermarketItem
class FakeSupermarketSpider(scrapy.Spider):
name = 'FakeSupermarketSpider'
allowed_domains = ['fakesupermarket.com.py']
start_urls = ['http://www.fakesupermarket.com.py/category/10']
all_link_categories = [
'http://www.fakesupermarket.com.py/category/1218.aspx',
'http://www.fakesupermarket.com.py/category/1231.aspx']
def __init__(self):
self.declare_xpath()
def declare_xpath(self):
self.TitleXpath = "/html/body/div[1]/form/div[5]/div[6]/div/div[2]/div[1]/div/div[1]/div[2]/div/h1/text()"
self.LinkXpath = "/html/body/div[1]/form/@action"
self.PriceXpath = "/html/body/div[1]/form/div[5]/div[6]/div/div[2]/div[1]/div/div[1]/div[2]/div/div[3]/div/div/div[5]/span/text()"
self.NumSerieXpath = "/html/body/div[1]/form/div[5]/div[6]/div/div[2]/div[1]/div/div[1]/div[2]/div/div[3]/div/div/div[6]/text()"
self.LinkImgXpath = "/html/body/div[1]/form/div[5]/div[6]/div/div[2]/div[1]/div/div[1]/div[1]/div[3]/ul/li/img/@src"
self.UnitXpath = "/html/body/div[1]/form/div[5]/div[6]/div/div[2]/div[1]/div/div[1]/div[2]/div/div[3]/div/div/div[8]/div[1]/div/span/text()"
def parse(self,response):
for href in all_link_categories:
url = response.urljoin(href)
yield scrapy.Request(url=url, callback=self.parse_main_item)
def parse_main_item(self,response):
item = fakesupermarketItem()
Title = response.xpath(self.TitleXpath).extract()
Title = self.cleanText(self.parseText(self.listToStr(Title)))
Link = response.xpath(self.LinkXpath).extract()
Link = self.cleanText(self.parseText(Link))
Price = response.xpath(self.PriceXpath).extract()
Price = self.cleanText(self.parseText(self.listToStr(Price)))
NumSerie = response.xpath(self.NumSerieXpath).extract()
NumSerie = self.cleanText(self.parseText(self.listToStr(NumSerie)))
LinkImg = response.xpath(self.LinkImgXpath).extract()
LinkImg = self.cleanText(self.parseText(self.listToStr(LinkImg)))
Unit = response.xpath(self.UnitXpath).extract()
Unit = self.cleanText(self.parseText(Unit))
item['Title'] = Title
item['Link'] = Link
item['Price'] = Price
item['NumSerie'] = NumSerie
item['LinkImg'] = LinkImg
item['Unit'] = Unit
return item
我的想法是复制最终产品所在的所有链接（大约有300个）。 这些链接位于 all_link_categories 数组中。 （我认为有错误） 日志：
2021-01-12 20:14:40 [scrapy.core.engine] INFO: Spider opened
2021-01-12 20:14:40 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2021-01-12 20:14:40 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2021-01-12 20:14:40 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://www.fakesupermarket.com.py/robots.txt> (referer: None)
2021-01-12 20:14:41 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://www.fakesupermarket.com.py/category/10.aspx> (referer: None)
2021-01-12 20:14:42 [scrapy.core.scraper] ERROR: Spider error processing <GET http://www.fakesupermarket.com.py/category/10.aspx> (referer: None)
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/scrapy/utils/defer.py", line 120, in iter_errback
yield next(it)
File "/usr/local/lib/python3.8/dist-packages/scrapy/utils/python.py", line 353, in __next__
return next(self.data)
File "/usr/local/lib/python3.8/dist-packages/scrapy/utils/python.py", line 353, in __next__
return next(self.data)
File "/usr/local/lib/python3.8/dist-packages/scrapy/core/spidermw.py", line 62, in _evaluate_iterable
for r in iterable:
File "/usr/local/lib/python3.8/dist-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output
for x in result:
File "/usr/local/lib/python3.8/dist-packages/scrapy/core/spidermw.py", line 62, in _evaluate_iterable
for r in iterable:
File "/usr/local/lib/python3.8/dist-packages/scrapy/spidermiddlewares/referer.py", line 340, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/usr/local/lib/python3.8/dist-packages/scrapy/core/spidermw.py", line 62, in _evaluate_iterable
for r in iterable:
File "/usr/local/lib/python3.8/dist-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr>
return (r for r in result or () if _filter(r))
File "/usr/local/lib/python3.8/dist-packages/scrapy/core/spidermw.py", line 62, in _evaluate_iterable
for r in iterable:
File "/usr/local/lib/python3.8/dist-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr>
return (r for r in result or () if _filter(r))
File "/usr/local/lib/python3.8/dist-packages/scrapy/core/spidermw.py", line 62, in _evaluate_iterable
for r in iterable:
File "/root/fakesupermarketPrueba/fakesupermarketPrueba/spiders/spider.py", line 374, in parse
for href in all_link_categories:
NameError: name 'all_link_categories' is not defined
2021-01-12 20:14:42 [scrapy.core.engine] INFO: Closing spider (finished)
为了访问在
all_link_categoriesparseself.all_link_categories而不是
all_link_categories
for href in self.all_link_categories:
url = response.urljoin(href)
yield scrapy.Request(url=url, callback=self.parse_main_item)