From 62feffac4b6324c1adf176b41e5cbde7034e6940 Mon Sep 17 00:00:00 2001 From: guange <8863824@gmail.com> Date: Thu, 17 Jan 2019 22:46:46 +0800 Subject: [PATCH] . --- .../taobao/__pycache__/items.cpython-37.pyc | Bin 1838 -> 1854 bytes .../__pycache__/pipelines.cpython-37.pyc | Bin 4499 -> 4527 bytes .../__pycache__/settings.cpython-37.pyc | Bin 1163 -> 1168 bytes chapter1/crawler/taobao/settings.py | 123 ++++++++++++++++++ chapter1/crawler/taobao/spiders/jd.py | 2 +- chapter1/crawler/taobao/spiders/jd1.py | 2 +- 6 files changed, 125 insertions(+), 2 deletions(-) create mode 100644 chapter1/crawler/taobao/settings.py diff --git a/chapter1/crawler/taobao/__pycache__/items.cpython-37.pyc b/chapter1/crawler/taobao/__pycache__/items.cpython-37.pyc index aed5c8d06c073d40256cb936db0ac85ebf4207fc..3b602a38a2d7d65f49f4597c0d6fc29818694aeb 100644 GIT binary patch delta 146 zcmZ3-w~vq4iIrKGYTb#e-eCz}vZ7YF0yjVz}br6$+1N=Qos1x$gsmvmw=-Dl+xr9 z&yv(!KTY1r0?cxgia1b`YRA7nYrC^@;8RYF<{$Tb1tVjdvD!H9rGQi~6;GP245 hg>5HqWEN+XnS7T`l?|l6NCv1?e6l>d3^TV7Cji^F9-#mL diff --git a/chapter1/crawler/taobao/__pycache__/pipelines.cpython-37.pyc b/chapter1/crawler/taobao/__pycache__/pipelines.cpython-37.pyc index 0a8bcd20676dde467d7615d0215c66e196f108d6..c4897c47c22ba00c9d18936721965a9aa729f3fc 100644 GIT binary patch delta 252 zcmbQNyk42tiIYZY0HynC7_wLwFazZoC4pK}xWOb3nB)bMd|(o!n|}@~Sa%dy zHycp*3!rW$nC{7SyhfTO>_9_AB^jC-Q^e-5ft1%U1~X`i`xR*dT~(wCByO>kR2HO8 xKFMn+!%@XkP?Voinp|R)mzbN1-~m-^=HOFg;x++lU|{58jLH)#uP?LpyCuRFv$%jdB7wunBv6qz`UfRYT1T#P)M{R9#j0mNT2(f|Me diff --git a/chapter1/crawler/taobao/__pycache__/settings.cpython-37.pyc b/chapter1/crawler/taobao/__pycache__/settings.cpython-37.pyc index 1aaf7e38e09af9a3634c3ab3d898c52ebf03ccc6..f754777be4cbb8abfcc67ab016147a34ea73af4f 100644 GIT binary patch delta 61 zcmeC?oWRNL#LLUY00d8`I85Yj;uMP#O%V@f(3IFXZ5<<{++?U$Iaq>rrricYIXo_!~wvLgJYqBeo;pS?lZbmi{pqe6) I$viAA08mB@Jpcdz diff --git a/chapter1/crawler/taobao/settings.py b/chapter1/crawler/taobao/settings.py new file mode 100644 index 0000000..d73d1b6 --- /dev/null +++ b/chapter1/crawler/taobao/settings.py @@ -0,0 +1,123 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for taobao project +# +# For simplicity, this file contains only settings considered important or +# commonly used. You can find more settings consulting the documentation: +# +# https://doc.scrapy.org/en/latest/topics/settings.html +# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +BOT_NAME = 'taobao' + +SPIDER_MODULES = ['taobao.spiders'] +NEWSPIDER_MODULE = 'taobao.spiders' + + + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36' + +# Obey robots.txt rules +ROBOTSTXT_OBEY = False + +LOG_LEVEL='DEBUG' + + +SPLASH_URL = 'http://127.0.0.1:8050' + +# 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://doc.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 = True + +# Disable Telnet Console (enabled by default) +TELNETCONSOLE_ENABLED = True + +# 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://doc.scrapy.org/en/latest/topics/spider-middleware.html +#SPIDER_MIDDLEWARES = { +# 'taobao.middlewares.ZhihuSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'taobao.middlewares.ZhihuDownloaderMiddleware': 543, +#} + +DOWNLOADER_MIDDLEWARES = { + 'scrapy_splash.SplashCookiesMiddleware': 723, + 'scrapy_splash.SplashMiddleware': 725, + 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810, +} +#Splash自己的去重过滤器 +DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter' + + + +# Enable or disable extensions +# See https://doc.scrapy.org/en/latest/topics/extensions.html +#EXTENSIONS = { +# 'scrapy.extensions.telnet.TelnetConsole': None, +#} + +# Configure item pipelines +# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html +#ITEM_PIPELINES = { +# 'taobao.pipelines.ZhihuPipeline': 300, +#} + +ITEM_PIPELINES = {'taobao.pipelines.MyImagesPipeline': 300} + +IMAGES_STORE = '/tmp/taobao' + +# Enable and configure the AutoThrottle extension (disabled by default) +# See https://doc.scrapy.org/en/latest/topics/autothrottle.html +# 启用限速 +AUTOTHROTTLE_ENABLED = True +# The initial download delay +AUTOTHROTTLE_START_DELAY = 30 +# 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://doc.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' + +FEED_EXPORT_ENCODING='utf-8' + + +#HBASE_HOST = '106.75.85.84' +HBASE_HOST = '106.75.120.249' +HBASE_PORT = 40009 +HBASE_TABLE = 'jd' + +COMMENT_MAX_PAGE = 10 diff --git a/chapter1/crawler/taobao/spiders/jd.py b/chapter1/crawler/taobao/spiders/jd.py index 65d4fb9..5ddef03 100644 --- a/chapter1/crawler/taobao/spiders/jd.py +++ b/chapter1/crawler/taobao/spiders/jd.py @@ -114,7 +114,7 @@ class JdSpider(scrapy.Spider): print(shop) yield JDProductItem( - type=0, + type='0', name=name, price=price, url=url, diff --git a/chapter1/crawler/taobao/spiders/jd1.py b/chapter1/crawler/taobao/spiders/jd1.py index 605159b..97dca08 100644 --- a/chapter1/crawler/taobao/spiders/jd1.py +++ b/chapter1/crawler/taobao/spiders/jd1.py @@ -114,7 +114,7 @@ class Jd1Spider(scrapy.Spider): print(shop) yield JDProductItem( - type=1, + type='1', name=name, price=price, url=url,