变更

python爬虫/scrapy/scrapy04/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 = scrapy04.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = scrapy04

python爬虫/scrapy/scrapy04/scrapy04/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 Scrapy04Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

python爬虫/scrapy/scrapy04/scrapy04/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 Scrapy04SpiderMiddleware:
+    # 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 Scrapy04DownloaderMiddleware:
+    # 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)

python爬虫/scrapy/scrapy04/scrapy04/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 Scrapy04Pipeline:
+    def process_item(self, item, spider):
+        return item

python爬虫/scrapy/scrapy04/scrapy04/settings.py

@@ -0,0 +1,93 @@
+# Scrapy settings for scrapy04 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 = "scrapy04"
+
+SPIDER_MODULES = ["scrapy04.spiders"]
+NEWSPIDER_MODULE = "scrapy04.spiders"
+LOG_LEVEL = "WARNING"
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "scrapy04 (+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 = {
+#    "scrapy04.middlewares.Scrapy04SpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "scrapy04.middlewares.Scrapy04DownloaderMiddleware": 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 = {
+#    "scrapy04.pipelines.Scrapy04Pipeline": 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"
+
+# Set settings whose default value is deprecated to a future-proof value
+REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"

python爬虫/scrapy/scrapy04/scrapy04/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.

python爬虫/scrapy/scrapy04/scrapy04/spiders/a17k.py

@@ -0,0 +1,36 @@
+import scrapy
+
+
+class A17kSpider(scrapy.Spider):
+    name = "17k"
+    allowed_domains = ["www.17k.com"]
+    start_urls = ["http://www.17k.com/"]
+
+    def start_requests(self):
+        url = "https://passport.17k.com/ck/user/login"  # 登录页面url，需要F12勾选保留日志
+        name = "18742526670"
+        password = "abc88888888"
+        cookies = """
+        set_cookies ="accessToken=avatarUrl%3Dhttps%253A%252F%252Fcdn.static.17k.com%252Fuser%252Favatar%252F18%252F98%252F61%252F99416198.jpg-88x88%253Fv%253D1667958854000%26id%3D99416198%26nickname%3Ddsjhb4353%26e%3D1740277543%26s%3Dc92fb8c95d438c9e; expires=Sun, 23-Feb-2025 02:25:43 GMT; Max-Age=15552000; path=/; domain=17k.com"
+        """
+        dict={}
+        list = cookies.split("; ")
+        for li in list:
+            k, v = li.split("=")
+            dict[k.strip()]=v.strip()
+
+
+        yield scrapy.Request(
+            url=self.start_urls,
+            cookies=dict,
+
+            # method="post",
+            # body="loginName=18742526670&password=abc88888888",  # 字符串，可在f12中复制
+            # callback=self.parse
+        )
+
+    def parse(self, response):
+        yield scrapy.Request(url=A17kSpider.start_urls[0], callback=self.parse_detail)
+
+    def parse_detail(self, response):
+        print(response.text)

python爬虫/scrapy/scrapy04/scrapy04/spiders/request.py

@@ -0,0 +1,7 @@
+import requests
+
+re = requests.get("https://www.17k.com/", headers={
+    "Cookie": """acw_tc=2760829c17247223199787197e955af4967a09151cf263b020ed11530b3a05; GUID=7fcdf02e-d9b6-4e9a-a853-3e40fdc041f1; acw_sc__v2=66cd2c9022caf54464293b12b74ff4e91646d41c; BAIDU_SSP_lcr=https://www.bing.com/; sajssdk_2015_cross_new_user=1; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%227fcdf02e-d9b6-4e9a-a853-3e40fdc041f1%22%2C%22%24device_id%22%3A%221919176265423-012e8869177da4-4c657b58-2073600-19191762655376%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E8%87%AA%E7%84%B6%E6%90%9C%E7%B4%A2%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22https%3A%2F%2Fwww.bing.com%2F%22%2C%22%24latest_referrer_host%22%3A%22www.bing.com%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC%22%7D%7D; Hm_lvt_9793f42b498361373512340937deb2a0=1724722325; Hm_lpvt_9793f42b498361373512340937deb2a0=1724722325; HMACCOUNT=5124896214E027AE; ssxmod_itna=eqjhD57KDIxmopDzgDUjftgDCwqiw5Au05n9KDsqDcYxA5D8D6DQeGTbus5dWdt76GPLW4vQDittFj8rXae3p8gvW=ZEx0aDbqGkonWi4GGUxBYDQxAYDGDDpkDj4ibDY+tODjnz/Zl61KDpxGrDlKDRx0749KDbxDaDGaksjDxdnF8DeKD0xD1K9OGDDPDaxy4DGy464nxm6DDEnI1ChAG3/O49=0D6xG1DQ5Ds242O9O25XDs92LXRIROK8YDvxDk=bvH3FxC/h5ORbhaGYrF5Yx5E0extBDxo0RDOpibqZr7rY2ZmBk4tGDrhNKDSYpN3ADD=; ssxmod_itna2=eqjhD57KDIxmopDzgDUjftgDCwqiw5Au05nKikAdDlh4QFd08D+6YD=="""
+    })
+
+print(re.text)