提交代码

Author: cxhuan

fans/README.md

@@ -16,7 +16,7 @@ Python技术 公众号文章代码库
 
 [PyAutoGUI，轻松搞定图片上传！](https://github.com/JustDoPython/python-examples/tree/master/fans/imgupload)：PyAutoGUI，轻松搞定图片上传！
 
-
+[为了买车，我爬了懂车帝！](https://github.com/JustDoPython/python-examples/tree/master/fans/scrapydcd)：为了买车，我爬了懂车帝！
 
 
 

fans/scrapydcd/dcd/dcd/__init__.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+import time
+from selenium import webdriver
+from scrapy.http.response.html import HtmlResponse
+
+class DcdDownloaderMiddleware(object):
+
+    def __init__(self):
+        # 加载测试浏览器
+        options = webdriver.ChromeOptions()
+        options.add_argument('--no-sandbox')
+        options.add_argument('--disable-gpu')
+        options.add_argument('--ignore-certificate-errors')
+        options.add_argument('--ignore-ssl-errors')
+
+        self.driver = webdriver.Chrome(executable_path=r"C:\drf2\drf2\chromedriver.exe",options=options)
+        self.driver.maximize_window()
+
+    #重写process_request方法
+    def process_request(self, request, spider):
+        print('request.url',request.url)
+        self.driver.get(request.url)
+        js = 'return document.body.scrollHeight;'
+        height = 0
+        if request.url != 'https://www.dongchedi.com/auto/library/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x':
+            while True:
+                new_height = self.driver.execute_script(js)
+                if new_height > height:
+                    self.driver.execute_script('window.scrollTo(0, document.body.scrollHeight)')
+                    height = new_height
+                    time.sleep(1)
+                else:
+                    print("滚动条已经处于页面最下方!")
+                    break
+        source = self.driver.page_source
+        # 创建一个response对象,把页面信息都封装在reponse对象中
+        response = HtmlResponse(url=self.driver.current_url,body=source,request = request,encoding="utf-8")
+        return response

fans/scrapydcd/dcd/dcd/__pycache__/__init__.cpython-37.pyc

@@ -0,0 +1,17 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DcdItem(scrapy.Item):
+    #品牌
+    brand = scrapy.Field()
+    #车型
+    name = scrapy.Field()
+    #评分
+    score = scrapy.Field()
+    #特点
+    title = scrapy.Field()

fans/scrapydcd/dcd/dcd/__pycache__/chrom_middlewares.cpython-37.pyc

@@ -0,0 +1,125 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+import time
+from selenium import webdriver
+from scrapy import signals
+from scrapy.http.response.html import HtmlResponse
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class DcdSpiderMiddleware:
+    # 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 DcdDownloaderMiddleware:
+    # 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.
+
+    def __init__(self):
+        # 加载测试浏览器
+        options = webdriver.ChromeOptions()
+        options.add_argument('--no-sandbox')
+        options.add_argument('--disable-gpu')
+        options.add_argument('--ignore-certificate-errors')
+        options.add_argument('--ignore-ssl-errors')
+
+        self.driver = webdriver.Chrome(executable_path=r"C:\drf2\drf2\chromedriver.exe",options=options)
+        self.driver.maximize_window()
+
+    @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):
+        print('request.url',request.url)
+        self.driver.get(request.url)
+        js = 'return document.body.scrollHeight;'
+        height = 0
+        if request.url != 'https://www.dongchedi.com/auto/library/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x':
+            while True:
+                new_height = self.driver.execute_script(js)
+                if new_height > height:
+                    self.driver.execute_script('window.scrollTo(0, document.body.scrollHeight)')
+                    height = new_height
+                    time.sleep(1)
+                else:
+                    print("滚动条已经处于页面最下方!")
+                    break
+        source = self.driver.page_source
+        # 创建一个response对象,把页面信息都封装在reponse对象中
+        response = HtmlResponse(url=self.driver.current_url,body=source,request = request,encoding="utf-8")
+        return response
+
+    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)

fans/scrapydcd/dcd/dcd/__pycache__/items.cpython-37.pyc

@@ -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 DcdPipeline:
+    def process_item(self, item, spider):
+        return item

fans/scrapydcd/dcd/dcd/__pycache__/settings.cpython-37.pyc

@@ -0,0 +1,88 @@
+# Scrapy settings for dcd 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 = 'dcd'
+
+SPIDER_MODULES = ['dcd.spiders']
+NEWSPIDER_MODULE = 'dcd.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'dcd (+http://www.yourdomain.com)'
+
+# 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 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 = {
+#    'dcd.middlewares.DcdSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+   'dcd.chrom_middlewares.DcdDownloaderMiddleware': 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 = {
+#    'dcd.pipelines.DcdPipeline': 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'

fans/scrapydcd/dcd/dcd/chrom_middlewares.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.

fans/scrapydcd/dcd/dcd/items.py

@@ -0,0 +1,47 @@
+import scrapy
+from lxml import etree
+from dcd.items import DcdItem
+import os,csv
+
+if os.path.exists('D:/桌面/car.csv'):
+    print('delete?')
+    os.remove('D:/桌面/car.csv')
+f = open('D:/桌面/car.csv', 'a+', newline='', encoding='gb18030')
+f_csv = csv.writer(f)
+f_csv.writerow(['品牌','车型', '评分', '特点'])
+class RainSpider(scrapy.Spider):
+    name = 'car'
+    allowed_domains = ['https://www.dongchedi.com/']
+    #url中的73代表吉利，18是奇瑞，35是长安，对这3个品牌发起请求
+    start_urls = ['https://www.dongchedi.com/auto/library/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-73-x-x','https://www.dongchedi.com/auto/library/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-18-x-x','https://www.dongchedi.com/auto/library/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-35-x-x']
+
+    def parse(self, response):
+        print('html111')
+        html =etree.HTML(response.text)
+
+        item = DcdItem()
+        brand = html.xpath('//*[@id="__next"]/div[1]/div[2]/div/div[4]/span[2]/div/div/a/text()')[0]
+        lis = html.xpath('//*[@id="__next"]/div[1]/div[2]/div/ul/li[position()>= 1]')
+        print('111 lis',lis)
+        for li in lis:
+            name = li.xpath('./div/a[1]/text()')[0]
+            try:
+                #有评分
+                score = li.xpath('./div/a[2]/text()')[0].split('分')[0]
+            except Exception as e:
+                #无评分
+                score = 0
+            try:
+                #有标题
+                title = li.xpath('./div/span/text()')[0]
+                # print('title111',title)
+            except Exception as e:
+                #无标题
+                title = '无'
+            print(name,score,title)
+            f_csv.writerow([brand,name,score,title])
+
+        item['name'] = name
+        item['score'] = score
+        item['title'] = title
+        yield item

fans/scrapydcd/dcd/dcd/middlewares.py

@@ -0,0 +1,3 @@
+from scrapy.cmdline import execute
+
+execute('scrapy crawl car'.split(' '))

fans/scrapydcd/dcd/dcd/pipelines.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+import json, re, requests, ssl
+from bs4 import BeautifulSoup
+from multiprocessing.dummy import Pool as ThreadPool
+
+url_list = []
+num_list = []
+brand_dict = {}
+
+
+def get_brand_id(num):
+    x = 'https://www.dongchedi.com/auto/library/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-%s-x-x' % num
+    rep = requests.get(x, timeout=10)
+    soup = BeautifulSoup(rep.text, 'html.parser')
+    condition = soup.find_all('span', class_='layout_label__1qfS8')
+    # 当num大于500时，有可能没这个品牌，condition[5]会报错
+    try:
+        s = condition[5].next_sibling.a.text
+        print('s111', s)
+        url_list.append(x)
+    except Exception as e:
+        pass
+
+    for span in condition:
+        if span.string == '已选条件':
+            print('ok')
+            brand_dict[s] = num
+            num_list.append(num)
+
+
+pool = ThreadPool(10)
+pool.map(get_brand_id, [i for i in range(1, 1000)])
+print(num_list)
+print(brand_dict)
+print(url_list)