# 用框架爬取兄弟连老师姓名
# xdl.py
# -*- coding: utf-8 -*-
import scrapy
class XdlSpider(scrapy.Spider):
name = 'xdl'
# allowed_domains = ['www.xdl.cn']
start_urls = ['http://www.itxdl.cn/activity/teacher/teacher_lieibiao/']
def parse(self, response):
# print(response.body.decode('utf-8'))
# print(response.status)
teacher_list = response.xpath('//div[@class="php_jiangshi_liebiao"]')
for teacher in teacher_list:
name = teacher.xpath('.//h1/text()')[0].extract()
print(name)
# main.py
from scrapy import cmdline
cmdline.execute('scrapy crawl xdl'.split())
# 爬取结果如下：
C:\Users\cz\AppData\Local\Programs\Python\Python35\python.exe E:/Python/python爬虫/baidu_test/baidu_test/spiders/main.py
2018-04-09 19:06:50 [scrapy.utils.log] INFO: Scrapy 1.5.0 started (bot: baidu_test)
2018-04-09 19:06:50 [scrapy.utils.log] INFO: Versions: lxml 4.2.1.0, libxml2 2.9.5, cssselect 1.0.3, parsel 1.4.0, w3lib 1.19.0, Twisted 17.9.0, Python 3.5.4 (v3.5.4:3f56838, Aug 8 2017, 02:17:05) [MSC v.1900 64 bit (AMD64)], pyOpenSSL 17.5.0 (OpenSSL 1.1.0h 27 Mar 2018), cryptography 2.2.2, Platform Windows-7-6.1.7601-SP1
2018-04-09 19:06:50 [scrapy.crawler] INFO: Overridden settings: {'NEWSPIDER_MODULE': 'baidu_test.spiders', 'SPIDER_MODULES': ['baidu_test.spiders'], 'BOT_NAME': 'baidu_test'}
2018-04-09 19:06:50 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.logstats.LogStats',
'scrapy.extensions.corestats.CoreStats']
2018-04-09 19:06:50 [scrapy.middleware] INFO: Enabled downloader middlewares:
['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']
2018-04-09 19:06:51 [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']
2018-04-09 19:06:51 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2018-04-09 19:06:51 [scrapy.core.engine] INFO: Spider opened
2018-04-09 19:06:51 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2018-04-09 19:06:51 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023
2018-04-09 19:06:51 [scrapy.core.engine] DEBUG: Crawled (200) <GET http://www.itxdl.cn/activity/teacher/teacher_lieibiao/> (referer: None)
李超
高洛峰
李明
张晓光
李剑华
张涛
陈玉龙
沈超
张诚
丛浩
管长龙
陈龙
2018-04-09 19:06:51 [scrapy.core.engine] INFO: Closing spider (finished)
2018-04-09 19:06:51 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 245,
'downloader/request_count': 1,
'downloader/request_method_count/GET': 1,
'downloader/response_bytes': 27993,
'downloader/response_count': 1,
'downloader/response_status_count/200': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2018, 4, 9, 11, 6, 51, 238181),
'log_count/DEBUG': 2,
'log_count/INFO': 7,
'response_received_count': 1,
'scheduler/dequeued': 1,
'scheduler/dequeued/memory': 1,
'scheduler/enqueued': 1,
'scheduler/enqueued/memory': 1,
'start_time': datetime.datetime(2018, 4, 9, 11, 6, 51, 24169)}
2018-04-09 19:06:51 [scrapy.core.engine] INFO: Spider closed (finished)
Process finished with exit code 0
兄弟连学python
Python学习交流、资源共享群：563626388 QQ