Adding scrapy project

.idea/RespoDL.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectLevelVcsManager" settingsEditedManually="false">
+    <OptionsSetting value="true" id="Add" />
+    <OptionsSetting value="true" id="Remove" />
+    <OptionsSetting value="true" id="Checkout" />
+    <OptionsSetting value="true" id="Update" />
+    <OptionsSetting value="true" id="Status" />
+    <OptionsSetting value="true" id="Edit" />
+    <ConfirmationsSetting value="0" id="Add" />
+    <ConfirmationsSetting value="0" id="Remove" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.5.2 (/usr/bin/python3.5)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/RespoDL.iml" filepath="$PROJECT_DIR$/.idea/RespoDL.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

RespoDL/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class RespodlItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    file_urls = scrapy.Field()
+    files = scrapy.Field()
+    image_urls = scrapy.Field()
+    images = scrapy.Field()

RespoDL/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class RespodlPipeline(object):
+    def process_item(self, item, spider):
+        return item

RespoDL/settings.py

+# -*- coding: utf-8 -*-
+import os
+
+# Scrapy settings for RespoDL project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'RespoDL'
+
+SPIDER_MODULES = ['RespoDL.spiders']
+NEWSPIDER_MODULE = 'RespoDL.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'RespoDL.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'RespoDL.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'scrapy.pipelines.images.ImagesPipeline': 1,
+    'scrapy.pipelines.files.FilesPipeline': 2
+}
+
+CUR_DIR = os.path.dirname(os.path.realpath(__file__))
+
+FILES_STORE = os.path.join(CUR_DIR, '..', 'files')
+FILES_URLS_FIELD = 'file_urls'
+FILES_RESULT_FIELD = 'files'
+
+IMAGES_STORE = os.path.join(CUR_DIR, '..', 'images')
+IMAGES_URLS_FIELD = 'image_urls'
+IMAGES_RESULT_FIELD = 'images'
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.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 http://scrapy.readthedocs.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'

RespoDL/spiders/DownloadSpider.py

+# Author: 陈闻超
+# Version: 1.0
+
+import scrapy
+import codecs
+import os
+
+class DownloadSpider(scrapy.Spider):
+
+    def write_file(self, filename, source):
+        os.makedirs(os.path.dirname(filename), exist_ok=True)
+        with codecs.open(filename, 'wb', 'utf-8') as f:
+            f.write(source)
\ No newline at end of file

RespoDL/spiders/HuaianshiSpider.py

+# Author: 陈闻超
+# Version: 1.0
+
+import re
+
+from scrapy import Request
+from scrapy import FormRequest
+
+from RespoDL.spiders import DownloadSpider
+
+class HuaianshiSpider(DownloadSpider):
+    name = 'huaianshi'
+    start_urls = ['http://222.184.118.98/haportal/jsp/portal/allportalPublicityList.do']
+
+    def build_page_request(self, page):
+        return FormRequest("http://222.184.118.98/haportal/jsp/portal/allportalPublicityList.do",
+                                  formdata={'formOrigin': '0',
+                                            'page': str(page)},
+                                  headers={
+                                      'referer': 'http://222.184.118.98/haportal/jsp/portal/allportalPublicityList.do'},
+                                  callback=self.parse,)
+
+    def parse(self, response):
+        cur_page = response.css("div.mainbody table tr td span::text").extract_first().strip()
+        filename = 'downloads/' + self.name + '/page_' + cur_page + '/' + cur_page
+        self.write_file(filename, response.text)
+
+        rows = response.css("div.list tr")[1:]
+        for row in rows:
+            cells = row.css("td")
+            url = cells.css("a p::attr('onclick')").extract_first()
+            url = re.search('\d+', url).group(0)
+            url = response.urljoin('allportalPublicityView.do?formId=' + url)
+            yield Request(url, meta={'page': cur_page}, callback=self.parse_detail)
+
+        last_page = response.css("div.mainbody table tr td span::text").extract()[1].strip()
+        if int(cur_page) < int(last_page):
+            yield self.build_page_request(int(cur_page)+1)
+
+    def parse_detail(self, response):
+        page = response.request.meta['page']
+        page_source = response.text
+        page_source = re.sub(r'charset=gb2312\"', 'charset=\"gb2312\"', page_source)
+        filename = 'downloads/' + self.name + '/page_' + page + '/' + response.url.split("?")[-1]
+        self.write_file(filename, page_source)
\ No newline at end of file

scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = RespoDL.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = RespoDL