我想用scrapy爬取谷歌应用市场，代码没有报错，但是却爬取不到内容，这是为什么？
# -*- coding: utf-8 -*-
import scrapy
# from scrapy.spiders import CrawlSpider, Rule
# from scrapy.linkextractors import LinkExtractor
from gp.items import GpItem
# from html.parser import HTMLParser as SGMLParser
import requests
class GoogleSpider(scrapy.Spider):
name = 'google'
allowed_domains = ['https://play.google.com/']
start_urls = ['https://play.google.com/store/apps/']
'''
rules = [
Rule(LinkExtractor(allow=("https://play\.google\.com/store/apps/details",)), callback='parse_app', follow=True),
]
'''
def parse(self, response):
selector = scrapy.Selector(response)
urls = selector.xpath('//a[@class="LkLjZd ScJHi U8Ww7d xjAeve nMZKrb id-track-click"]/@href').extract()
link_flag = 0
links = []
for link in urls:
links.append(link)
for each in urls:
yield scrapy.Request(links[link_flag], callback=self.parse_next, dont_filter=True)
link_flag += 1
def parse_next(self, response):
selector = scrapy.Selector(response)
app_urls = selector.xpath('//div[@class="details"]/a[@class="title"]/@href').extract()
print(app_urls)
urls = []
for url in app_urls:
url = "http://play.google.com" + url
print(url)
urls.append(url)
link_flag = 0
for each in app_urls:
yield scrapy.Request(urls[link_flag], callback=self.parse_app, dont_filter=True)
link_flag += 1
def parse_app(self, response):
item = GpItem()
item['app_url'] = response.url
item['app_name'] = response.xpath('//div[@itemprop="name"]').xpath('text()').extract()
item['app_icon'] = response.xpath('//img[@itempro="image"]/@src')
item['app_developer'] = response.xpath('//')
print(response.text)
yield item
terminal运行信息如下：
BettyMacbookPro-764:gp zhanjinyang$ scrapy crawl google
2019-11-12 08:46:45 [scrapy.utils.log] INFO: Scrapy 1.6.0 started (bot: gp)
2019-11-12 08:46:45 [scrapy.utils.log] INFO: Versions: lxml 4.2.5.0, libxml2 2.9.8, cssselect 1.0.3, parsel 1.5.1, w3lib 1.20.0, Twisted 19.2.1, Python 3.7.1 (default, Dec 14 2018, 13:28:58) - [Clang 4.0.1 (tags/RELEASE_401/final)], pyOpenSSL 18.0.0 (OpenSSL 1.1.1a 20 Nov 2018), cryptography 2.4.2, Platform Darwin-18.5.0-x86_64-i386-64bit
2019-11-12 08:46:45 [scrapy.crawler] INFO: Overridden settings: {'BOT_NAME': 'gp', 'NEWSPIDER_MODULE': 'gp.spiders', 'ROBOTSTXT_OBEY': True, 'SPIDER_MODULES': ['gp.spiders'], 'USER_AGENT': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36'}
2019-11-12 08:46:45 [scrapy.extensions.telnet] INFO: Telnet Password: b2d7dedf1f4a91eb
2019-11-12 08:46:45 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.memusage.MemoryUsage',
'scrapy.extensions.logstats.LogStats']
2019-11-12 08:46:45 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2019-11-12 08:46:45 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2019-11-12 08:46:45 [scrapy.middleware] INFO: Enabled item pipelines:
['gp.pipelines.GpPipeline']
2019-11-12 08:46:45 [scrapy.core.engine] INFO: Spider opened
2019-11-12 08:46:45 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2019-11-12 08:46:45 [py.warnings] WARNING: /anaconda3/lib/python3.7/site-packages/scrapy/spidermiddlewares/offsite.py:61: URLWarning: allowed_domains accepts only domains, not URLs. Ignoring URL entry https://play.google.com/ in allowed_domains.
warnings.warn(message, URLWarning)
2019-11-12 08:46:45 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2019-11-12 08:46:45 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://play.google.com/robots.txt> (referer: None)
2019-11-12 08:46:46 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://play.google.com/store/apps/> (referer: None)
2019-11-12 08:46:46 [scrapy.core.engine] INFO: Closing spider (finished)
2019-11-12 08:46:46 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 810,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 232419,
'downloader/response_count': 2,
'downloader/response_status_count/200': 2,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2019, 11, 12, 8, 46, 46, 474543),
'log_count/DEBUG': 2,
'log_count/INFO': 9,
'log_count/WARNING': 1,
'memusage/max': 58175488,
'memusage/startup': 58175488,
'response_received_count': 2,
'robotstxt/request_count': 1,
'robotstxt/response_count': 1,
'robotstxt/response_status_count/200': 1,
'scheduler/dequeued': 1,
'scheduler/dequeued/memory': 1,
'scheduler/enqueued': 1,
'scheduler/enqueued/memory': 1,
'start_time': datetime.datetime(2019, 11, 12, 8, 46, 45, 562775)}
2019-11-12 08:46:46 [scrapy.core.engine] INFO: Spider closed (finished)
求助！！！
