huya.py
# -*- coding: utf-8 -*-
import scrapy
from huyaPro1.items import Huyapro1Item
class HuyaSpider(scrapy.Spider):
name = 'huya'
# allowed_domains = ['www.xxx.com']
start_urls = ['https://www.huya.com/g/xingxiu']
def parse(self, response):
li_list = response.xpath('//*[@id="js-live-list"]/li')
for li in li_list:
title = li.xpath('./a[2]/text()').extract_first()
# title = li.xpath('./a[2]/text()').extract()
author = li.xpath('./span/span[1]/i/text()').extract_first()
hot = li.xpath('./span/span[2]/i[2]/text()').extract_first()
# print(title, type(title))
# print(author, type(author))
# print(hot, type(hot))
item = Huyapro1Item()
item['title'] = title
item['author'] = author
item['hot'] = hot
yield item
items.py
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class Huyapro1Item(scrapy.Item):
# define the fields for your item here like:
title = scrapy.Field()
author = scrapy.Field()
hot = scrapy.Field()
middlewares.py——
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class Huyapro1SpiderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the spider middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_spider_input(self, response, spider):
# Called for each response that goes through the spider
# middleware and into the spider.
# Should return None or raise an exception.
return None
def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response.
# Must return an iterable of Request, dict or Item objects.
for i in result:
yield i
def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception.
# Should return either None or an iterable of Request, dict
# or Item objects.
pass
def process_start_requests(self, start_requests, spider):
# Called with the start requests of the spider, and works
# similarly to the process_spider_output() method, except
# that it doesn’t have a response associated.
# Must return only requests (not items).
for r in start_requests:
yield r
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
class Huyapro1DownloaderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the downloader middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_request(self, request, spider):
# Called for each request that goes through the downloader
# middleware.
# Must either:
# - return None: continue processing this request
# - or return a Response object
# - or return a Request object
# - or raise IgnoreRequest: process_exception() methods of
# installed downloader middleware will be called
return None
def process_response(self, request, response, spider):
# Called with the response returned from the downloader.
# Must either;
# - return a Response object
# - return a Request object
# - or raise IgnoreRequest
return response
def process_exception(self, request, exception, spider):
# Called when a download handler or a process_request()
# (from other downloader middleware) raises an exception.
# Must either:
# - return None: continue processing this exception
# - return a Response object: stops process_exception() chain
# - return a Request object: stops process_exception() chain
pass
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
pipelines.py
# -*- coding: utf-8 -*-
# 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
import pymysql
from redis import Redis
class Huyapro1Pipeline(object):
fp = None
def open_spider(self, spider):
self.fp = open('huyazhibo.txt', 'w', encoding='utf-8')
def process_item(self, item, spider):
self.fp.write(item['title'] + ':' + item['author'] + ':' + item['hot'] + '\n')
print(item['title'], '写入成功!!!')
return item
def close_spider(self, spider):
self.fp.close()
class mysqlPipeLine(object):
conn = None
cursot = None
def open_spider(self, spider):
self.conn = pymysql.Connect(host='127.0.0.1', port=3306, user='root', password='123', db='Spider',
charset='utf8')
print(self.conn)
def process_item(self, item, spider):
sql = 'insert into huya values("%s","%s","%s")' % (item['title'], item['author'], item['hot'])
self.cursot = self.conn.cursor()
try:
self.cursot.execute(sql)
self.conn.commit()
except Exception as e:
print(e)
self.conn.rollback()
return item
def close_spider(self, spider):
self.cursot.close()
self.conn.close()
class RedisPipeLine(object):
conn = None
def open_spider(self, spider):
self.conn = Redis(host='127.0.0.1', port=6379)
def process_item(self, item, spider):
self.conn.lpush('huyalist', item)
return item
settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for huyaPro1 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 = 'huyaPro1'
SPIDER_MODULES = ['huyaPro1.spiders']
NEWSPIDER_MODULE = 'huyaPro1.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
LOG_LEVEL = 'ERROR'
# 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 = {
# 'huyaPro1.middlewares.Huyapro1SpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# 'huyaPro1.middlewares.Huyapro1DownloaderMiddleware': 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 = {
'huyaPro1.pipelines.Huyapro1Pipeline': 300,
'huyaPro1.pipelines.mysqlPipeLine': 301,
'huyaPro1.pipelines.RedisPipeLine': 302,
}
# 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'