想爬取多页面数据(从一个页面的多个链接中获取更进一步详情),然后通过管道把数据导入到excel文件中,能够运行该程序不出错,但是excel文件中没有任何数据
doctor.py
import scrapy
from scrapy import Selector,Request
#from scrapy.http import Request
from scrapy.http import HtmlResponse
from scrapy_doctor.items import ScrapyDoctorItem
#from scrapy.linkextractors import LinkExtractor
#from scrapy.spiders import CrawlSpider,Rule
class DoctorSpider(scrapy.Spider):
name = "doctor"
allowed_domains = ["so.120ask.com"]
#start_urls = ["http://so.120ask.com/?kw=%E6%8A%91%E9%83%81&page=1&isloc=1"]
#url='http://so.120ask.com/?kw=%E6%8A%91%E9%83%81&page=%d&isloc=1'
#page=1
def start_requests(self):
for page in range(2):
yield Request(url=f'http://so.120ask.com/?kw=%E6%8A%91%E9%83%81&page={page + 1}&isloc=1')
def parse(self, response:HtmlResponse ):
sel=Selector(response)
list_items=sel.css('#datalist > li')
for list_item in list_items :
detail_url = list_item.css('h3 > a::attr(href)').extract_first()
yield Request(url="http:" + detail_url, callback=self.parse_detail)
def parse_detail(self,response):
sel = Selector(response)
doctor_item=kwargs ['item']
doctor_item=ScrapyDoctorItem()
doctor_item['doctorInformation']=sel.css('span[class="b_sp1"]::text').extract_first()
doctor_item['goodAt'] = sel.css('span[class="b_sp2"]::text').extract_first()
doctor_item['question'] = sel.css('h1[id="askH1"]::text').extract_first()
doctor_item['answer'] = sel.css('div[class="crazy_new"]::text').extract_first()
yield doctor_item
item.py
import scrapy
class ScrapyDoctorItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# 医生信息
doctorInformation = scrapy.Field()
# 擅长
goodAt = scrapy.Field()
# 问题
question = scrapy.Field()
# 回答
answer = scrapy.Field()
pipelines.py
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# useful for handling different item types with a single interface
import csv
import openpyxl
#from itemadapter import ItemAdapter
class ScrapyDoctorPipeline:
def __init__(self):
#self.fp = open('book.json', 'w', encoding='utf-8')
self.wb=openpyxl.Workbook ()
self.ws=self.wb.active
self.ws.title='Doctor'
self.ws.append(('医生信息','擅长','问题','回答'))
def close_spider(self, spider):
self.wb.save('百度健康抑郁问答.xlsx')
#self.csv_file.close()
def process_item(self, item, spider):
#self.csv_writer.writerow(ItemAdapter(item).asdict())
doctorInformation=item.get('doctorInformation','')
goodAt=item.get('goodAt','')
question=item.get('question','')
answer=item.get('answer','')
self.ws.append((doctorInformation,goodAt,question,answer))
return item
settings.py
# Scrapy settings for scrapy_doctor project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://docs.scrapy.org/en/latest/topics/settings.html
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = "scrapy_doctor"
SPIDER_MODULES = ["scrapy_doctor.spiders"]
NEWSPIDER_MODULE = "scrapy_doctor.spiders"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
# "Accept-Language": "en",
#}
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# "scrapy_doctor.middlewares.ScrapyDoctorSpiderMiddleware": 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# "scrapy_doctor.middlewares.ScrapyDoctorDownloaderMiddleware": 543,
#}
# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# "scrapy.extensions.telnet.TelnetConsole": None,
#}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
"scrapy_doctor.pipelines.ScrapyDoctorPipeline": 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = "httpcache"
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage"
# Set settings whose default value is deprecated to a future-proof value
#REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
#TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
#FEED_EXPORT_ENCODING = "utf-8"
#ITEM_PIPELINES = {
# 管道可以有很多个 那么管道是有优先级 优先级的范围是1到1000 值越小优先级越高
#'scrapy_doctor.pipelines.ScrapyDoctorPipeline': 300,
#}