Add files via upload

Author: danielshashko

README.md

@@ -0,0 +1,54 @@
+
+import requests
+from bs4 import BeautifulSoup
+import csv
+
+# URL of the page to scrape
+url = "https://en.wikipedia.org/wiki/Web_scraping"
+
+# Send a GET request to the URL and get the response
+response = requests.get(url)
+
+# Get the HTML content of the page
+html = response.text
+
+# Parse the HTML content with BeautifulSoup
+soup = BeautifulSoup(html, "html.parser")
+
+# List where to store the scraped titles
+titles = []
+
+# List of header levels (h1, h2, h3, h4, h5)
+title_level_list = [1, 2, 3, 4, 5]
+
+# Loop through each header level (h1, h2, h3, h4, h5)
+for title_level in title_level_list:
+    # Find all elements of the current header level
+    title_elements = soup.find_all(f"h{title_level}")
+
+    # Loop through each title element found
+    for title_element in title_elements:
+        # Data extraction logic
+        tag = title_element.name
+        text = title_element.text
+
+        # Create a dictionary with the tag and the title text
+        title = {
+            "tag": tag,
+            "title": text,
+        }
+
+        # Append the dictionary to the titles list
+        titles.append(title)
+
+# Open a CSV file to write the data
+with open("titles.csv", mode="w", newline="", encoding="utf-8") as file:
+    # Create a CSV writer object and specify the fieldnames (columns)
+    writer = csv.DictWriter(file, fieldnames=["tag", "title"])
+
+    # Write the header (column names) to the CSV file
+    writer.writeheader()
+
+    # Write each row (dictionary) to the CSV file
+    for row in titles:
+        writer.writerow(row)

requests-beautifulsoup-scraper.py

@@ -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 = scrapy_scraping.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = scrapy_scraping

scrapy_scraping/scrapy.cfg

@@ -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 ScrapyScrapingItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

scrapy_scraping/scrapy_scraping/__init__.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 ScrapyScrapingSpiderMiddleware:
+    # 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 ScrapyScrapingDownloaderMiddleware:
+    # 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_scraping/scrapy_scraping/__pycache__/__init__.cpython-311.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 ScrapyScrapingPipeline:
+    def process_item(self, item, spider):
+        return item

scrapy_scraping/scrapy_scraping/__pycache__/settings.cpython-311.pyc

@@ -0,0 +1,92 @@
+# Scrapy settings for scrapy_scraping 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 = "scrapy_scraping"
+
+SPIDER_MODULES = ["scrapy_scraping.spiders"]
+NEWSPIDER_MODULE = "scrapy_scraping.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "scrapy_scraping (+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 = {
+#    "scrapy_scraping.middlewares.ScrapyScrapingSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "scrapy_scraping.middlewares.ScrapyScrapingDownloaderMiddleware": 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 = {
+#    "scrapy_scraping.pipelines.ScrapyScrapingPipeline": 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
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"

scrapy_scraping/scrapy_scraping/items.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_scraping/scrapy_scraping/middlewares.py

@@ -0,0 +1,31 @@
+import scrapy
+
+
+class WikipediaSpider(scrapy.Spider):
+    name = "wikipedia"
+    allowed_domains = ["en.wikipedia.org"]
+    start_urls = ["https://en.wikipedia.org/wiki/Web_scraping"]
+
+    def parse(self, response):
+        # List to store the titles
+        titles = []
+
+        # List of header levels (h1, h2, h3, h4, h5)
+        title_level_list = [1, 2, 3, 4, 5]
+
+        # Loop through each header level (h1, h2, h3, h4, h5)
+        for title_level in title_level_list:
+            # Find all elements of the current header level
+            title_elements = response.css(f"h{title_level}")
+
+            # Loop through each title element found
+            for title_element in title_elements:
+                # Extract tag and text
+                tag = title_element.root.tag
+                text = title_element.css("::text").get().strip()
+
+                # Yield the data directly to the feed
+                yield {
+                    "tag": tag,
+                    "title": text,
+                }

scrapy_scraping/scrapy_scraping/pipelines.py

@@ -0,0 +1,22 @@
+tag,title
+h1,Web scraping
+h2,Contents
+h2,History
+h2,Techniques
+h2,Legal issues
+h2,Methods to prevent web scraping
+h2,See also
+h2,References
+h3,Human copy-and-paste
+h3,Text pattern matching
+h3,HTTP programming
+h3,HTML parsing
+h3,DOM parsing
+h3,Vertical aggregation
+h3,Semantic annotation recognizing
+h3,Computer vision web-page analysis
+h3,AI-powered document understanding
+h3,United States
+h3,European Union
+h3,Australia
+h3,India