更新简书回复

Scrapy/vie/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 = vie.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = vie

Scrapy/vie/start.py

@@ -0,0 +1,6 @@
+"""
+    Created by 朝南而行 2018/12/21 14:23
+"""
+from scrapy import cmdline
+
+cmdline.execute('scrapy crawl vie_language'.split())

Scrapy/vie/vie/items.py

@@ -0,0 +1,15 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class VieItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    base_url = scrapy.Field()
+    filename = scrapy.Field()

Scrapy/vie/vie/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class VieSpiderMiddleware(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 Response, 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 VieDownloaderMiddleware(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)

Scrapy/vie/vie/pipelines.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import os
+import requests
+from contextlib import closing
+
+
+class ViePipeline(object):
+    def __init__(self):
+        # __file__ 当前文件的目录
+        # os.path.dirname 相当于 cd ..
+        # os.path.join 路径的拼接
+        # os.path.exists 判断路径是否存在，如果path存在，返回True；如果path不存在，返回False
+        self.path = os.path.join(os.path.dirname(__file__), 'mp4')
+        if not os.path.exists(self.path):
+            os.mkdir(self.path)
+            print('路径不存在')
+        else:
+            print('路径存在')
+
+    def process_item(self, item, spider):
+        base_url = item['base_url']
+        filename = item['filename']
+
+        with closing(requests.get(base_url, stream=True)) as response:
+            chunk_size = 1024  # 单次请求最大值
+            content_size = int(response.headers['content-length'])  # 内容体总大小
+            data_count = 0
+            with open(os.path.join(self.path, filename), "wb") as file:
+                for data in response.iter_content(chunk_size=chunk_size):
+                    file.write(data)
+                    data_count = data_count + len(data)
+                    now_jd = (data_count / content_size) * 100
+                    print("\r 文件下载进度：%d%%(%d/%d) - %s" %
+                          (now_jd, data_count, content_size, base_url), end=" ")

Scrapy/vie/vie/settings.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for vie 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 = 'vie'
+
+SPIDER_MODULES = ['vie.spiders']
+NEWSPIDER_MODULE = 'vie.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'vie (+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://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 = 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',
+  'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
+}
+
+# Enable or disable spider middlewares
+# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'vie.middlewares.VieSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'vie.middlewares.VieDownloaderMiddleware': 543,
+#}
+
+# 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 = {
+   'vie.pipelines.ViePipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://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 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'

Scrapy/vie/vie/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.

Scrapy/vie/vie/spiders/vie_language.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from vie.items import VieItem
+
+
+class VieLanguageSpider(scrapy.Spider):
+    name = 'vie_language'
+    allowed_domains = ['sound2.yywz123.com']
+    start_urls = ['http://sound2.yywz123.com']
+
+    def parse(self, response):
+        # url = 'http://sound2.yywz123.com/vie/tingli/yngq/{}.mp3'
+
+        # for x in range(600, 757):
+        #     base_url = url.format(x)
+        #     filename = base_url.split('/')[-1]
+        #     yield VieItem(base_url=base_url, filename=filename)
+
+        url = 'http://v.kd1.qq.com/shg_321_1116_22X0000000dz1HEhRVd3d5c1bc4a4739.f620.mp4' \
+              '?dis_k=4f0cb86283d2b08cb728afd3dcff6c38&dis_t=1545790690'
+
+        filename = url.split('?')[0].split('_')[-1].replace('.', '', 1)
+
+        yield VieItem(base_url=url, filename=filename)