From c2bae541c77e43f2f0ae11ebcb1071236400ca02 Mon Sep 17 00:00:00 2001
From: hihell <q1t5o9e3@163.com>
Date: Mon, 25 Oct 2021 10:14:14 +0800
Subject: [PATCH] =?UTF-8?q?=E9=98=85=E6=96=87=E4=BD=9C=E5=AE=B6=E4=B8=AD?=
 =?UTF-8?q?=E5=BF=83=E7=88=AC=E8=99=AB?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 NO45/scrapy.cfg                               |  11 ++
 NO45/yuewen/__init__.py                       |   0
 .../__pycache__/__init__.cpython-37.pyc       | Bin 0 -> 147 bytes
 .../__pycache__/settings.cpython-37.pyc       | Bin 0 -> 279 bytes
 NO45/yuewen/items.py                          |  12 ++
 NO45/yuewen/middlewares.py                    | 103 ++++++++++++++++++
 NO45/yuewen/pipelines.py                      |  13 +++
 NO45/yuewen/settings.py                       |  89 +++++++++++++++
 NO45/yuewen/spiders/__init__.py               |   4 +
 .../__pycache__/__init__.cpython-37.pyc       | Bin 0 -> 155 bytes
 .../spiders/__pycache__/yw.cpython-37.pyc     | Bin 0 -> 1594 bytes
 NO45/yuewen/spiders/yw.py                     |  34 ++++++
 README.md                                     |   5 +-
 13 files changed, 270 insertions(+), 1 deletion(-)
 create mode 100644 NO45/scrapy.cfg
 create mode 100644 NO45/yuewen/__init__.py
 create mode 100644 NO45/yuewen/__pycache__/__init__.cpython-37.pyc
 create mode 100644 NO45/yuewen/__pycache__/settings.cpython-37.pyc
 create mode 100644 NO45/yuewen/items.py
 create mode 100644 NO45/yuewen/middlewares.py
 create mode 100644 NO45/yuewen/pipelines.py
 create mode 100644 NO45/yuewen/settings.py
 create mode 100644 NO45/yuewen/spiders/__init__.py
 create mode 100644 NO45/yuewen/spiders/__pycache__/__init__.cpython-37.pyc
 create mode 100644 NO45/yuewen/spiders/__pycache__/yw.cpython-37.pyc
 create mode 100644 NO45/yuewen/spiders/yw.py

diff --git a/NO45/scrapy.cfg b/NO45/scrapy.cfg
new file mode 100644
index 0000000..7d9e63b
--- /dev/null
+++ b/NO45/scrapy.cfg
@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = yuewen.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = yuewen
diff --git a/NO45/yuewen/__init__.py b/NO45/yuewen/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/NO45/yuewen/__pycache__/__init__.cpython-37.pyc b/NO45/yuewen/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..352f7e7f3a69f0aa104005137d300547e384109d
GIT binary patch
literal 147
zcmZ?b<>g`kg7A=tL=gQLM8E(ekl_Ht#VkM~g&~+hlhJP_LlH<AL436Ya$T)r3Mxx7
z^78_U^0QKtOJbgPta&kWwV{#0lYQOK=B#--XG4sMX-s8lYI$m2OniK1US>&ryk0@&
UEe@O9{FKt1R6CHVpMjVG0FXo{5&!@I

literal 0
HcmV?d00001

diff --git a/NO45/yuewen/__pycache__/settings.cpython-37.pyc b/NO45/yuewen/__pycache__/settings.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..38ac59b39e4cc753817649eac329245b46d7d99d
GIT binary patch
literal 279
zcmZ?b<>g`kf{=>bL=GMXhQ}Zd3@`#24nSNi1td}!q8L&b(;1@}Qy8O|QkbHcQ<$Sz
zQdoi+G+CqADoaz#Q}e3$Ahcd_L1s#7QL)=C_Hf4_KTkh*KTXzK98Ufr@qUiJuDAGt
z13X<^gW`StT|#|agKr7=xrU<%-Qo-K2dWMZi3o}JcXExq#p&bk9`EBC=IXPOp@<#m
z95C_K63BA3iYcfp$;i(OD9X=DO)iOf-m&Jz%+-cQ22b{NKby1W>6{HQCZ;hEm&FvP
mmXu`Xr5EcJRNmsS$<0qG%}KQb1wk<fkYHhAV`O1xaRmU!=}$ud

literal 0
HcmV?d00001

diff --git a/NO45/yuewen/items.py b/NO45/yuewen/items.py
new file mode 100644
index 0000000..5addc6d
--- /dev/null
+++ b/NO45/yuewen/items.py
@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class YuewenItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
diff --git a/NO45/yuewen/middlewares.py b/NO45/yuewen/middlewares.py
new file mode 100644
index 0000000..c8da86a
--- /dev/null
+++ b/NO45/yuewen/middlewares.py
@@ -0,0 +1,103 @@
+# 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
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class YuewenSpiderMiddleware:
+    # 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, 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 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 YuewenDownloaderMiddleware:
+    # 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)
diff --git a/NO45/yuewen/pipelines.py b/NO45/yuewen/pipelines.py
new file mode 100644
index 0000000..db7958b
--- /dev/null
+++ b/NO45/yuewen/pipelines.py
@@ -0,0 +1,13 @@
+# 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
+from itemadapter import ItemAdapter
+
+
+class YuewenPipeline:
+    def process_item(self, item, spider):
+        return item
diff --git a/NO45/yuewen/settings.py b/NO45/yuewen/settings.py
new file mode 100644
index 0000000..371cbd6
--- /dev/null
+++ b/NO45/yuewen/settings.py
@@ -0,0 +1,89 @@
+# Scrapy settings for yuewen 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 = 'yuewen'
+
+SPIDER_MODULES = ['yuewen.spiders']
+NEWSPIDER_MODULE = 'yuewen.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'yuewen (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'yuewen.middlewares.YuewenSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'yuewen.middlewares.YuewenDownloaderMiddleware': 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 = {
+#    'yuewen.pipelines.YuewenPipeline': 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'
+LOG_LEVEL = 'WARNING'
diff --git a/NO45/yuewen/spiders/__init__.py b/NO45/yuewen/spiders/__init__.py
new file mode 100644
index 0000000..ebd689a
--- /dev/null
+++ b/NO45/yuewen/spiders/__init__.py
@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.
diff --git a/NO45/yuewen/spiders/__pycache__/__init__.cpython-37.pyc b/NO45/yuewen/spiders/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..149125917c57e784ca09836f816d436ded7990e5
GIT binary patch
literal 155
zcmZ?b<>g`kg7A=t#DzfmF^B^Lj6jA15Erumi4=xl22Do4l?+87VFdBj5y*A5iYcfp
z$;i(OD9X=DO)iOf-m&Jz%+-cQ22b{NKby1W>6{HQCZ;i!rK#nqc`?NWnJKA7#WC^m
dnR%Hd@$q^EmA5!-a`RJ4b5iX<rhf)v1^`eCD-i$y

literal 0
HcmV?d00001

diff --git a/NO45/yuewen/spiders/__pycache__/yw.cpython-37.pyc b/NO45/yuewen/spiders/__pycache__/yw.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..f9a35912012722e95a7629c504cd93e584c6414b
GIT binary patch
literal 1594
zcmbVMOKTiQ5bmDG?sy;CwJjw!A%{Sa83*mkCLuwwY!M-H2}`g|4wDVz@pP{>_Po^H
z%X*hJ1nfh==m!LRkd7ff<Pz{HKcufw9{vHjr>b|gmV|Rj4_(z={iv_Ls-7>J%^HFB
z{xpkr972A_$#H`@*@7-V1HlNRDG5+pDb1|FqByowJ97dja|4%>F9~y)`;0J`J5TMP
z!ss31S6;(u((|cqewE~pb{;Dc#i|g#rR&=w8l`v2gmIyr+ryN{xc9iZFxY}F?}6YX
zpo|0-qk+w=2Q+Y)4btTmUPZ6_lvP-D-!gNLor8Ie)%UG|6?m+{n$JjZjxDhk=o)LY
z^PubO0=o#h!IlB%iuShe&#(m6cr<B@M51_SZ?6*<+2qq*rAoQc?VhxD%R;Cq?M6Z+
zamsHEl2mbVcU<z#_0=+Zz&Ec=);m{^x5Y)Sc&_@l;wWL8efH7nfOBTHUtdk*ne9U$
z%8k;r80lIW3CTl1k%7^R!FoT69}V9HI=bEH+bxx-ly6=+diDJ1)%ULtf4%Y@>}v@w
zl}KV0J}x7*EAN7>GAQuI*n*STP}|UvZg~lWg6uw}lqh;&G3$_iLomC*irt&6tgWq;
zqKLVaA>2Jol?2QGX2iF(TZ$xCx*}r{m1AAK&G&`?8Y;q(JRN8c+>}Kw`A<Z&0o^~J
zgV@>Vmt(bC<X?;8A&*u6uOD9i{o~KquCE{c_WaKmFaLP)OaJ3f`r{!V@w_ihQOW*z
z)Bz8z8Iw{$roy2}&tu$J-h_H|a_Knloip2F<OmyT<ZK(dTn4e=i%c!#&2VM?7gs(N
zbvWePVhNOJfzZ`Cl_tQMKvV$rG}S9$d@Iz`+ZL(Cs1R<9=Wc>H0hK;9NuJJ=d|)5K
z1HMcSoI~=&O2`v?YE5nC+#pkXQ2=gl(#8T<lp^N7ZYpnMLveV`6r5<+SbWz6s%_v{
z+p(0oiaX%FYZr^M^qn^p2n<a-Sl(wy5LH;Y3|%%rV2*0^9qM4NE}qF1o{kX#Hq_Wn
znve*S7TPn{LlO-8SWqYUc1>g-fKi&)K_^S6UG)5>_QEiaG9HGy7KT~D;7<kPMi}l5
zqjbLFpw=z(bU6!Ikwr-^b!|~}QXnLOUbHLV3Mnq20qe;`EZ)P>8+>MjMIrD{Sb;9_
zfCo%eXvJ<@%eLph=b3fCDv&L`GJ92>6n?gI@(UqnZkOh3^VcD;P-dvm!`obI@5U_N
On@Frg5FTyNw*4=p3!9Aq

literal 0
HcmV?d00001

diff --git a/NO45/yuewen/spiders/yw.py b/NO45/yuewen/spiders/yw.py
new file mode 100644
index 0000000..a3205b5
--- /dev/null
+++ b/NO45/yuewen/spiders/yw.py
@@ -0,0 +1,34 @@
+import scrapy
+from scrapy.linkextractors import LinkExtractor
+from scrapy.spiders import CrawlSpider, Rule
+
+
+class CbSpider(CrawlSpider):
+    name = 'yw'
+    allowed_domains = ['write.qq.com']
+    start_urls = ['https://write.qq.com/portal/article?filterType=0&page=1']
+    # URL 提取规则
+    rules = (
+        Rule(LinkExtractor(allow=r'.*/portal/content\?caid=\d+&feedType=2&lcid=\d+$'), callback="parse_item"),
+        # 寻找下一页 url 地址
+        Rule(LinkExtractor(restrict_xpaths="//a[@title='下一页']"), follow=True),
+    )
+
+    def parse_start_url(self, response):
+        print("---process_results---")
+        yield scrapy.Request('https://write.qq.com/portal/article?filterType=0&page=1')
+
+    def process_results(self, response, results):
+        print("---process_results---")
+        print(results)
+
+    def parse_item(self, response):
+        print("---parse_item---")
+        print(response.url)
+        title = response.css('title::text').extract()[0].strip()
+        item = {}
+        item["title"] = title
+        yield item
+
+    def parse(self):
+        pass
\ No newline at end of file
diff --git a/README.md b/README.md
index 169ec4e..3ebcbc2 100644
--- a/README.md
+++ b/README.md
@@ -85,5 +85,8 @@
 
 ### 📘 scrapy 库学习 
 
-
+42. [学python，怎么能不学习scrapy呢，这篇博客带你学会它](https://dream.blog.csdn.net/article/details/120899494)
+43. [python scrapy 管道学习，并拿在行练手爬虫项目](https://dream.blog.csdn.net/article/details/120934425)
+44. [python scrapy极细拆解，打开Spider类看内容，顺手爬了一下优设网](https://dream.blog.csdn.net/article/details/120936534)
+45. [练手练到阅文集团作家中心了，python crawlspider 二维抓取学习](https://dream.blog.csdn.net/article/details/120835220)
 
-- 
GitLab