变更

python爬虫/python爬虫练习/git/git/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 GitItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

python爬虫/python爬虫练习/git/git/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 GitSpiderMiddleware:
+    # 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 GitDownloaderMiddleware:
+    # 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/python爬虫练习/git/git/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 GitPipeline:
+    def process_item(self, item, spider):
+        return item

python爬虫/python爬虫练习/git/git/settings.py

@@ -0,0 +1,95 @@
+# Scrapy settings for git 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 = "git"
+
+SPIDER_MODULES = ["git.spiders"]
+NEWSPIDER_MODULE = "git.spiders"
+LOG_LEVEL="WARNING"
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Edg/127.0.0.0"
+
+TLDEXTRACT_CACHE_DIR = False
+
+# 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 = {
+#    "git.middlewares.GitSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "git.middlewares.GitDownloaderMiddleware": 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 = {
+#    "git.pipelines.GitPipeline": 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/python爬虫练习/git/git/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/python爬虫练习/git/git/spiders/git2.py

@@ -0,0 +1,41 @@
+import scrapy
+
+# 使用FormRequest发送post请求
+
+class Git2Spider(scrapy.Spider):
+    name = "git2"
+    allowed_domains = ["github.com"]
+    start_urls = ["https://github.com/login"]
+
+    def parse(self, response):
+        # 从登录页面解析出post数据
+        token = response.xpath('//input[@name="authenticity_token"]/@value').extract_first()
+
+        post_data = {
+            'commit': 'Sign in',
+            'authenticity_token': token,
+            'login': ' 1415243231@qq.com',
+            'password': ' zy18742526670',
+            'webauthn-conditional': ' undefined',
+            'javascript-support': ' true',
+            'webauthn-support': ' supported',
+            'webauthn-iuvpaa-support': ' supported',
+            'return_to': 'https://github.com/login',
+            'timestamp': ' 1726731919711',
+            'timestamp_secret': '51cd0dd93807a1fdb0095203af8d9f45d864a1f3ca83b1268f6f659624804398'
+        }
+
+        # print(post_data)
+        # 针对url发送post请求
+        yield scrapy.FormRequest(
+            url="https://github.com/session",
+            callback=self.after_login,
+            formdata=post_data
+        )
+
+    def after_login(self, response):
+        yield scrapy.Request('https://github.com/PandaltsGo',callback=self.check_log)
+
+    def check_log(self,response):
+        title = response.xpath('//*[@id="581032515"]/span/text()').extract_first()
+        print(title)

python爬虫/python爬虫练习/git/git/spiders/github.py

@@ -0,0 +1,24 @@
+import scrapy
+
+#直接携带cookie字典请求
+
+class GithubSpider(scrapy.Spider):
+    name = "github"
+    allowed_domains = ["github.com"]
+    start_urls = ["https://github.com/PandaltsGo"]
+
+    def start_requests(self):
+        url =self.start_urls[0]
+        cookies = '''_gh_sess=5ZDPStPAYwzU0t3by%2FpHC4UL4Fs2AiwfHyrhWN6C0vsUEpjtEVW5bjJGNIc6Lc8UfftkYNh2EYJzpcTsFIaEjnn6TfigTP0tcBvenlfICTwnJKidXXqEFgWdo2ou5gCBj%2BZMr0qS%2Bbf437FjJm0nuv0kcZiEI17sqfWkgL9UrTnievN62FcXakNMSXmxGdal12MQTHcA9makPHYPqdAm9J9w2%2BKnJKZXBeHnHB9pvYq5IZYHN%2BhndueA6W5%2B3M5%2FgwMdi0dniIyLiW7kgsD1ntV%2BclB4YUaiSBSut6PwonD9GlEyJYef%2FRlITnwWKyoNKpaWZy9SzLuDrS1vWI5z46Na2DDCjU5TqKdFI2afUfIq0JhTzkvUk40SnIHRZ2hZrzJd7t8cDfCDQronozMZscurF1mIHnITDSnQjHp0FImtVw1lbiuiMHyQ%2Bw41V9GM0TiRmJgZIWZ5F4I5kI68W%2FgM%2F5hRNlRrF26EWVmYTSINIfnkuY5kFThjK04OwoMCVd0d3yCua5qf%2FWX3XXl4Jzoj09JfqovsdqqezdAjzju06oVy5xh2RJz6VjA0BBTrxbVgBB91ybZ61XqdbWxXnm9AI9y6Y7AyY%2FUZp4BemfigBVdSE2gpU3S3VbwrmcjEzoAM8hv%2Bp37ROkl45teQ6aRE4Yh2xF26MYaMY5ffzjrweqfjeqIPJZO4qyIxEPNs7OTmzMTp87w1FodO6ZTdy0PvX1JVuHfVlHQuQUzo6ClrKaNsL0Fld7BahIEIgi8AbHRJyLgS7jsw1xhbRQ4ZCcvMRS%2B%2BBd%2Bh6KSEV27lX1dCNogvPRjFah38bFcbj35tw4pOUqdBkj%2BtvMKmQVLPrBJ%2BAa6lTjJqZa4s3P6uB5Ac%2BIMF--RnCQu9IfXR19B%2B3g--ZjZab0obtWOBIHl5EF%2FWRQ%3D%3D; path=/; secure; HttpOnly;'''
+        cookies = {data.split('=')[0]:data.split('=')[-1] for data in cookies.split(';')}
+
+        yield scrapy.Request(
+            url=url,
+            cookies=cookies,
+            callback=self.parse
+        )
+
+
+    def parse(self, response):
+        title = response.xpath('//*[@id="581032515"]/span/text()').extract_first()
+        print(title)

python爬虫/python爬虫练习/git/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 = git.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = git