Then check out ScrapeOps, the complete toolkit for web scraping.
config.json
file inside.{"api_key": "your-super-secret-api-key"}
.import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] def get_scrapeops_url(url, location="us"): payload = { "api_key": API_KEY, "url": url, "country": location, "wait": 5000, "residential": True, } proxy_url = "https://proxy.scrapeops.io/v1/?" + urlencode(payload) return proxy_url ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) @dataclassclass ProductData: name: str = "" price: str = "" rating: float = 0.0 review_count: int = 0 details: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: scrapeops_proxy_url = get_scrapeops_url(url, location=location) response = requests.get(scrapeops_proxy_url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages ) def process_product(row, location, retries=3): url = row["url"] tries = 0 success = False while tries <= retries and not success: response = requests.get(get_scrapeops_url(url, location=location)) try: if response.status_code == 200: logger.info(f"Status: {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") title = soup.select_one("h1[data-test='product-title']").text rating = "n/a" review_count = 0 rating_holder = soup.select_one("span[data-test='ratings']") if rating_holder: rating_array = rating_holder.text.split(" ") rating = rating_array[0] review_count = rating_array[-2] price_holder = soup.select_one("span[data-test='product-price']") price = price_holder.text details = soup.select_one("div[data-test='productDetailTabs-itemDetailsTab']").text product_pipeline = DataPipeline(csv_filename=f"{row['name'].replace(' ', '-')}.csv") product_data = ProductData( name=title, price=price, rating=rating, review_count=review_count, details=details ) product_pipeline.add_data(product_data) product_pipeline.close_pipeline() success = True else: logger.warning(f"Failed Response: {response.status_code}") raise Exception(f"Failed Request, status code: {response.status_code}") except Exception as e: logger.error(f"Exception thrown: {e}") logger.warning(f"Failed to process page: {row['url']}, retries left: {retries-tries}") tries += 1 if not success: raise Exception(f"Max Retries exceeded: {retries}") else: logger.info(f"Successfully parsed: {row['url']}") def process_results(csv_file, location, max_threads=5, retries=3): logger.info(f"processing {csv_file}") with open(csv_file, newline="") as file: reader = list(csv.DictReader(file)) with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( process_product, reader, [location] * len(reader), [retries] * len(reader) ) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 2 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.") for file in aggregate_files: process_results(file, LOCATION, max_threads=MAX_THREADS, retries=MAX_RETRIES)
MAX_RETRIES
: Determines the maximum number of retries the script will attempt if a request fails (e.g., due to a network issue or a non-200 status code).MAX_THREADS
: Defines the number of concurrent threads used during the scraping and processing tasks.PAGES
: Specifies the number of pages to scrape for each keyword. Each page typically contains a set of search results.LOCATION
: Sets the location/country code for the scraping requests. It is passed to the proxy URL to simulate requests coming from a specific region.keyword_list
: Contains the list of keywords for which you want to scrape data. Each keyword corresponds to a separate search query on the Target website.python name_of_your_file.py
.
dict
objects.https://www.target.com/s?searchTerm={formatted_keyword}
https://www.target.com/s?searchTerm=laptop
https://www.target.com/p/{name-of-item}/-/some-other-stuff
https://www.target.com/p/hp-15-6-34-fhd-laptop-intel-core-i5-8gb-ram-512gb-ssd-storage-silver-15-fd0075tg/-/A-89476632#lnk=sametab
div
. This div
has a data-test
value of @web/site-top-of-funnel/ProductCardWrapper
. We'll use these elements to extract our link and title.
Nao
parameter. When you go to page 2, you'll see Nao=24
in the URL. Our full URLs are laid out like this:
https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}
country
param into our URL.
"country": "us"
."country": "uk"
.mkdir target-scraper cd target-scraper
python -m venv venv
source venv/bin/activate
pip install requests
pip install beautifulsoup4
scrape_search_results()
, it's our parsing function.
import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) def scrape_search_results(keyword, location, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}" tries = 0 success = False while tries <= retries and not success: try: response = requests.get(url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = { "name": name, "url": link, } print(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") scrape_search_results(keyword, LOCATION, retries=MAX_RETRIES) logger.info(f"Crawl complete.")
a
elements.href
with a_tags[0].get("href")
.href
with some string splitting."https://www.target.com"
to our href
.Nao
parameter to control our pagination, Nao={page_number*24}
to be more precise. Page 2 starts with Nao=24
, so we when we find our pages, we'll start counting at 0.
https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}
start_scrape()
.
def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): for page in range(pages): scrape_search_results(keyword, location, page, data_pipeline=data_pipeline, retries=retries)
import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) def scrape_search_results(keyword, location, page_number, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: response = requests.get(url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = { "name": name, "url": link, } print(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): for page in range(pages): scrape_search_results(keyword, location, page, data_pipeline=data_pipeline, retries=retries) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") start_scrape(keyword, PAGES, LOCATION, retries=MAX_RETRIES) logger.info(f"Crawl complete.")
Nao
parameter is used to control our pagination.start_scrape()
gives us the ability to crawl multiple pages at once.SearchData
and DataPipeline
.
Take a look at SearchData
, we use it to hold each item's title and URL.
@dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip())
DataPipeline
. We feed it SearchData
objects and it pipes them to a CSV file. Not only does it pipe them to a CSV, but it also checks and removes duplicate items based on their name
.
class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv()
DataPipeline
and pass our SearchData
objects into it.
import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: response = requests.get(url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, retries=3): for page in range(pages): scrape_search_results(keyword, location, page, data_pipeline=data_pipeline, retries=retries) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.")
SearchData
class is used to represent actual results from our search.DataPipeline
pipes our results into a CSV file.ThreadPoolExecutor
to give us multithreading support. Then on each available thread, we'll call scrape_search_results()
.
Here is our updated start_scrape()
function.
def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages )
executor.map()
:
scrape_search_results()
: the function we want to call on each thread.[keyword * pages]
: our keyword
as an array the size of our pages.[location * pages]
: our location
as an array the size of our pages.range(pages)
: our list of pages.[data_pipeline * page]
: our data_pipeline
passed in as an array the size of our pages.[retries * pages]
: our retries
passed in as an array the size of our page list.import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: response = requests.get(url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages ) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.")
def get_scrapeops_url(url, location="us"): payload = { "api_key": API_KEY, "url": url, "country": location, "wait": 5000, "residential": True, } proxy_url = "https://proxy.scrapeops.io/v1/?" + urlencode(payload) return proxy_url
payload
as well:
"api_key"
: our ScrapeOps API key."url"
: the url we want to scrape."country"
: the country we want to appear in."wait"
: the amount of time we want the server to wait before sending our response."residential"
: a boolean. If we want to a residential IP address, we set this to True
.import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] def get_scrapeops_url(url, location="us"): payload = { "api_key": API_KEY, "url": url, "country": location, "wait": 5000, "residential": True, } proxy_url = "https://proxy.scrapeops.io/v1/?" + urlencode(payload) return proxy_url ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: scrapeops_proxy_url = get_scrapeops_url(url, location=location) response = requests.get(scrapeops_proxy_url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages ) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.")
main
below.
if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 2 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.")
MAX_RETRIES
: Determines the maximum number of retries the script will attempt if a request fails (e.g., due to a network issue or a non-200 status code).MAX_THREADS
: Defines the number of concurrent threads used during the scraping and processing tasks.PAGES
: Specifies the number of pages to scrape for each keyword. Each page typically contains a set of search results.LOCATION
: Sets the location/country code for the scraping requests. It is passed to the proxy URL to simulate requests coming from a specific region.keyword_list
: Contains the list of keywords for which you want to scrape data. Each keyword corresponds to a separate search query on the Target website.process_product()
.
def process_product(row, location, retries=3): url = row["url"] tries = 0 success = False while tries <= retries and not success: response = requests.get(url, location=location) try: if response.status_code == 200: logger.info(f"Status: {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") title = soup.select_one("h1[data-test='product-title']").text rating = "n/a" review_count = 0 rating_holder = soup.select_one("span[data-test='ratings']") if rating_holder: rating_array = rating_holder.text.split(" ") rating = rating_array[0] review_count = rating_array[-2] price_holder = soup.select_one("span[data-test='product-price']") price = price_holder.text details = soup.select_one("div[data-test='productDetailTabs-itemDetailsTab']").text product_data = { "name": title, "price": price, "rating": rating, "review_count": review_count, "details": details } print(product_data) success = True else: logger.warning(f"Failed Response: {response.status_code}") raise Exception(f"Failed Request, status code: {response.status_code}") except Exception as e: logger.error(f"Exception thrown: {e}") logger.warning(f"Failed to process page: {row['url']}, retries left: {retries-tries}") tries += 1 if not success: raise Exception(f"Max Retries exceeded: {retries}") else: logger.info(f"Successfully parsed: {row['url']}")
title = soup.select_one("h1[data-test='product-title']").text
is used to extract our title.rating
and review_count
to "n/a"
and 0
by default.rating
or review_count
present, we reassign it to its respective variable.soup.select_one("div[data-test='productDetailTabs-itemDetailsTab']").text
is used to find our details
.process_product()
on each item from the array.
def process_results(csv_file, location, retries=3): logger.info(f"processing {csv_file}") with open(csv_file, newline="") as file: reader = list(csv.DictReader(file)) for row in reader: process_product(row, location, retries=retries)
import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] def get_scrapeops_url(url, location="us"): payload = { "api_key": API_KEY, "url": url, "country": location, "wait": 5000, "residential": True, } proxy_url = "https://proxy.scrapeops.io/v1/?" + urlencode(payload) return proxy_url ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: scrapeops_proxy_url = get_scrapeops_url(url, location=location) response = requests.get(scrapeops_proxy_url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages ) def process_product(row, location, retries=3): url = row["url"] tries = 0 success = False while tries <= retries and not success: response = requests.get(url, location=location) try: if response.status_code == 200: logger.info(f"Status: {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") title = soup.select_one("h1[data-test='product-title']").text rating = "n/a" review_count = 0 rating_holder = soup.select_one("span[data-test='ratings']") if rating_holder: rating_array = rating_holder.text.split(" ") rating = rating_array[0] review_count = rating_array[-2] price_holder = soup.select_one("span[data-test='product-price']") price = price_holder.text details = soup.select_one("div[data-test='productDetailTabs-itemDetailsTab']").text product_data = { "name": title, "price": price, "rating": rating, "review_count": review_count, "details": details } print(product_data) success = True else: logger.warning(f"Failed Response: {response.status_code}") raise Exception(f"Failed Request, status code: {response.status_code}") except Exception as e: logger.error(f"Exception thrown: {e}") logger.warning(f"Failed to process page: {row['url']}, retries left: {retries-tries}") tries += 1 if not success: raise Exception(f"Max Retries exceeded: {retries}") else: logger.info(f"Successfully parsed: {row['url']}") def process_results(csv_file, location, retries=3): logger.info(f"processing {csv_file}") with open(csv_file, newline="") as file: reader = list(csv.DictReader(file)) for row in reader: process_product(row, location, retries=retries) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.") for file in aggregate_files: process_results(file, LOCATION, retries=MAX_RETRIES)
process_results()
is used to read our CSV file and iterate through it.process_product()
on each item from the array as we iterate.dataclass
. We'll call this one ProductData
. It holds the following fields:
name
price
rating
review_count
details
ProductData
class.
@dataclassclass ProductData: name: str = "" price: str = "" rating: float = 0.0 review_count: int = 0 details: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip())
DataPipeline
inside our parsing function and then pass a ProductData
object into it.
import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] def get_scrapeops_url(url, location="us"): payload = { "api_key": API_KEY, "url": url, "country": location, "wait": 5000, "residential": True, } proxy_url = "https://proxy.scrapeops.io/v1/?" + urlencode(payload) return proxy_url ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) @dataclassclass ProductData: name: str = "" price: str = "" rating: float = 0.0 review_count: int = 0 details: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: scrapeops_proxy_url = get_scrapeops_url(url, location=location) response = requests.get(scrapeops_proxy_url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages ) def process_product(row, location, retries=3): url = row["url"] tries = 0 success = False while tries <= retries and not success: response = requests.get(url, location=location) try: if response.status_code == 200: logger.info(f"Status: {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") title = soup.select_one("h1[data-test='product-title']").text rating = "n/a" review_count = 0 rating_holder = soup.select_one("span[data-test='ratings']") if rating_holder: rating_array = rating_holder.text.split(" ") rating = rating_array[0] review_count = rating_array[-2] price_holder = soup.select_one("span[data-test='product-price']") price = price_holder.text details = soup.select_one("div[data-test='productDetailTabs-itemDetailsTab']").text product_pipeline = DataPipeline(csv_filename=f"{row['name'].replace(' ', '-')}.csv") product_data = ProductData( name=title, price=price, rating=rating, review_count=review_count, details=details ) product_pipeline.add_data(product_data) product_pipeline.close_pipeline() success = True else: logger.warning(f"Failed Response: {response.status_code}") raise Exception(f"Failed Request, status code: {response.status_code}") except Exception as e: logger.error(f"Exception thrown: {e}") logger.warning(f"Failed to process page: {row['url']}, retries left: {retries-tries}") tries += 1 if not success: raise Exception(f"Max Retries exceeded: {retries}") else: logger.info(f"Successfully parsed: {row['url']}") def process_results(csv_file, location, retries=3): logger.info(f"processing {csv_file}") with open(csv_file, newline="") as file: reader = list(csv.DictReader(file)) for row in reader: process_product(row, location, retries=retries) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 1 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.") for file in aggregate_files: process_results(file, LOCATION, retries=MAX_RETRIES)
ThreadPoolExecutor
to call our parsing function on all available threads.
Take a look at our refactored process_results()
.
def process_results(csv_file, location, max_threads=5, retries=3): logger.info(f"processing {csv_file}") with open(csv_file, newline="") as file: reader = list(csv.DictReader(file)) with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( process_product, reader, [location] * len(reader), [retries] * len(reader) )
executor.map()
:
process_product
is the function we want to call on each thread.reader
is the array of items we wish to parse.get_scrapeops_url()
, we just need to use it in the right place. We'll change one line from within our parser.
response = requests.get(get_scrapeops_url(url, location=location))
import osimport csvimport requestsimport jsonimport loggingfrom urllib.parse import urlencodefrom bs4 import BeautifulSoupimport concurrent.futuresfrom dataclasses import dataclass, field, fields, asdict API_KEY = "" with open("config.json", "r") as config_file: config = json.load(config_file) API_KEY = config["api_key"] def get_scrapeops_url(url, location="us"): payload = { "api_key": API_KEY, "url": url, "country": location, "wait": 5000, "residential": True, } proxy_url = "https://proxy.scrapeops.io/v1/?" + urlencode(payload) return proxy_url ## Logginglogging.basicConfig(level=logging.INFO)logger = logging.getLogger(__name__) @dataclassclass SearchData: name: str = "" url: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) @dataclassclass ProductData: name: str = "" price: str = "" rating: float = 0.0 review_count: int = 0 details: str = "" def __post_init__(self): self.check_string_fields() def check_string_fields(self): for field in fields(self): # Check string fields if isinstance(getattr(self, field.name), str): # If empty set default text if getattr(self, field.name) == "": setattr(self, field.name, f"No {field.name}") continue # Strip any trailing spaces, etc. value = getattr(self, field.name) setattr(self, field.name, value.strip()) class DataPipeline: def __init__(self, csv_filename="", storage_queue_limit=50): self.names_seen = [] self.storage_queue = [] self.storage_queue_limit = storage_queue_limit self.csv_filename = csv_filename self.csv_file_open = False def save_to_csv(self): self.csv_file_open = True data_to_save = [] data_to_save.extend(self.storage_queue) self.storage_queue.clear() if not data_to_save: return keys = [field.name for field in fields(data_to_save[0])] file_exists = os.path.isfile(self.csv_filename) and os.path.getsize(self.csv_filename) > 0 with open(self.csv_filename, mode="a", newline="", encoding="utf-8") as output_file: writer = csv.DictWriter(output_file, fieldnames=keys) if not file_exists: writer.writeheader() for item in data_to_save: writer.writerow(asdict(item)) self.csv_file_open = False def is_duplicate(self, input_data): if input_data.name in self.names_seen: logger.warning(f"Duplicate item found: {input_data.name}. Item dropped.") return True self.names_seen.append(input_data.name) return False def add_data(self, scraped_data): if self.is_duplicate(scraped_data) == False: self.storage_queue.append(scraped_data) if len(self.storage_queue) >= self.storage_queue_limit and self.csv_file_open == False: self.save_to_csv() def close_pipeline(self): if self.csv_file_open: time.sleep(3) if len(self.storage_queue) > 0: self.save_to_csv() def scrape_search_results(keyword, location, page_number, data_pipeline=None, retries=3): formatted_keyword = keyword.replace(" ", "+") url = f"https://www.target.com/s?searchTerm={formatted_keyword}&Nao={page_number*24}" tries = 0 success = False while tries <= retries and not success: try: scrapeops_proxy_url = get_scrapeops_url(url, location=location) response = requests.get(scrapeops_proxy_url) logger.info(f"Recieved [{response.status_code}] from: {url}") if response.status_code != 200: raise Exception(f"Failed request, Status Code {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") div_cards = soup.select("div[data-test='@web/site-top-of-funnel/ProductCardWrapper']", recursive=False) for div_card in div_cards: a_tags = div_card.find_all("a") href = a_tags[0].get("href") name = href.split("/")[2] link = f"https://www.target.com{href}" search_data = SearchData( name=name, url=link, ) data_pipeline.add_data(search_data) logger.info(f"Successfully parsed data from: {url}") success = True except Exception as e: logger.error(f"An error occurred while processing page {url}: {e}") logger.info(f"Retrying request for page: {url}, retries left {retries-tries}") tries+=1 if not success: raise Exception(f"Max Retries exceeded: {retries}") def start_scrape(keyword, pages, location, data_pipeline=None, max_threads=5, retries=3): with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( scrape_search_results, [keyword] * pages, [location] * pages, range(pages), [data_pipeline] * pages, [retries] * pages ) def process_product(row, location, retries=3): url = row["url"] tries = 0 success = False while tries <= retries and not success: response = requests.get(get_scrapeops_url(url, location=location)) try: if response.status_code == 200: logger.info(f"Status: {response.status_code}") soup = BeautifulSoup(response.text, "html.parser") title = soup.select_one("h1[data-test='product-title']").text rating = "n/a" review_count = 0 rating_holder = soup.select_one("span[data-test='ratings']") if rating_holder: rating_array = rating_holder.text.split(" ") rating = rating_array[0] review_count = rating_array[-2] price_holder = soup.select_one("span[data-test='product-price']") price = price_holder.text details = soup.select_one("div[data-test='productDetailTabs-itemDetailsTab']").text product_pipeline = DataPipeline(csv_filename=f"{row['name'].replace(' ', '-')}.csv") product_data = ProductData( name=title, price=price, rating=rating, review_count=review_count, details=details ) product_pipeline.add_data(product_data) product_pipeline.close_pipeline() success = True else: logger.warning(f"Failed Response: {response.status_code}") raise Exception(f"Failed Request, status code: {response.status_code}") except Exception as e: logger.error(f"Exception thrown: {e}") logger.warning(f"Failed to process page: {row['url']}, retries left: {retries-tries}") tries += 1 if not success: raise Exception(f"Max Retries exceeded: {retries}") else: logger.info(f"Successfully parsed: {row['url']}") def process_results(csv_file, location, max_threads=5, retries=3): logger.info(f"processing {csv_file}") with open(csv_file, newline="") as file: reader = list(csv.DictReader(file)) with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor: executor.map( process_product, reader, [location] * len(reader), [retries] * len(reader) ) if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 2 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.") for file in aggregate_files: process_results(file, LOCATION, max_threads=MAX_THREADS, retries=MAX_RETRIES)
PAGES
to 2 and MAX_THREADS
to 5 just like we did earlier. If you need a refresher, here is our main
.
if __name__ == "__main__": MAX_RETRIES = 3 MAX_THREADS = 5 PAGES = 2 LOCATION = "us" logger.info(f"Crawl starting...") ## INPUT ---> List of keywords to scrape keyword_list = ["laptop"] aggregate_files = [] ## Job Processes for keyword in keyword_list: filename = keyword.replace(" ", "-") crawl_pipeline = DataPipeline(csv_filename=f"{filename}.csv") start_scrape(keyword, PAGES, LOCATION, data_pipeline=crawl_pipeline, max_threads=MAX_THREADS, retries=MAX_RETRIES) crawl_pipeline.close_pipeline() aggregate_files.append(f"{filename}.csv") logger.info(f"Crawl complete.") for file in aggregate_files: process_results(file, LOCATION, max_threads=MAX_THREADS, retries=MAX_RETRIES)
robots.txt
.
You can view Target's terms here. Their robots.txt
is available here.
If you're unsure of your scraper, you should talk to an attorney.