yad2-scraper 0.2.0__tar.gz → 0.4.0__tar.gz

{yad2_scraper-0.2.0 → yad2_scraper-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: yad2-scraper
-Version: 0.2.0
+Version: 0.4.0
 Summary: Scrape Yad2 in Python.
 License: LICENSE
 Author: dav ost

{yad2_scraper-0.2.0 → yad2_scraper-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "yad2-scraper"
-version = "0.2.0"
+version = "0.4.0"
 description = "Scrape Yad2 in Python."
 authors = ["dav ost <davidost2003@gmail.com>"]
 license = "LICENSE"

{yad2_scraper-0.2.0 → yad2_scraper-0.4.0}/yad2_scraper/constants.py

@@ -18,9 +18,10 @@ DEFAULT_REQUEST_HEADERS = {
 ALLOW_REQUEST_REDIRECTS = True
 VERIFY_REQUEST_SSL = True
 
-ANTIBOT_CONTENT = b"Are you for real"  # robot-captcha
+ANTIBOT_CONTENT_IDENTIFIER = b"Are you for real"  # robot-captcha
+PAGE_CONTENT_IDENTIFIER = b"https://www.yad2.co.il/"
 
-FIRST_PAGE = 1
+FIRST_PAGE_NUMBER = 1
 NOT_MENTIONED_PRICE_RANGE = 0, 0
 
 NEXT_DATA_SCRIPT_ID = "__NEXT_DATA__"

yad2_scraper-0.4.0/yad2_scraper/exceptions.py

@@ -0,0 +1,32 @@
+import httpx
+from typing import List, Union
+
+
+class ResponseError(Exception):
+    def __init__(self, msg: str, request: httpx.Request, response: httpx.Response):
+        super().__init__(msg)
+        self.request = request
+        self.response = response
+
+
+class AntiBotDetectedError(ResponseError):
+    pass
+
+
+class UnexpectedContentError(ResponseError):
+    pass
+
+
+class MaxAttemptsExceededError(Exception):
+    def __init__(self, msg: str, max_attempts: int, errors: List[BaseException] = None):
+        super().__init__(msg)
+        self.max_attempts = max_attempts
+        self.errors = errors
+
+
+class MaxRequestAttemptsExceededError(MaxAttemptsExceededError):
+    def __init__(self, method: str, url: str, max_attempts: int, errors: List[Union[httpx.HTTPError, ResponseError]]):
+        msg = f"All {max_attempts} attempts for {method} request to '{url}' have failed"
+        super().__init__(msg, max_attempts, errors)
+        self.method = method
+        self.url = url

yad2_scraper-0.4.0/yad2_scraper/scraper.py

@@ -0,0 +1,165 @@
+import logging
+import httpx
+import time
+from fake_useragent import FakeUserAgent
+from typing import Optional, Dict, Any, Callable, Union, Type, TypeVar
+
+from yad2_scraper.category import Yad2Category
+from yad2_scraper.query import QueryFilters
+from yad2_scraper.exceptions import AntiBotDetectedError, UnexpectedContentError, MaxRequestAttemptsExceededError
+from yad2_scraper.constants import (
+    DEFAULT_REQUEST_HEADERS,
+    ALLOW_REQUEST_REDIRECTS,
+    VERIFY_REQUEST_SSL,
+    ANTIBOT_CONTENT_IDENTIFIER,
+    PAGE_CONTENT_IDENTIFIER
+)
+
+Category = TypeVar("Category", bound=Yad2Category)
+WaitStrategy = Callable[[int], Optional[float]]
+QueryParamTypes = Union[QueryFilters, Dict[str, Any]]
+
+fua = FakeUserAgent()
+logger = logging.getLogger(__name__)
+
+
+class Yad2Scraper:
+    def __init__(
+            self,
+            client: Optional[httpx.Client] = None,
+            request_defaults: Optional[Dict[str, Any]] = None,
+            randomize_user_agent: bool = True,
+            wait_strategy: Optional[WaitStrategy] = None,
+            max_request_attempts: int = 1
+    ):
+        self.client = client or httpx.Client(
+            headers=DEFAULT_REQUEST_HEADERS,
+            follow_redirects=ALLOW_REQUEST_REDIRECTS,
+            verify=VERIFY_REQUEST_SSL
+        )
+        self.request_defaults = request_defaults or {}
+        self.randomize_user_agent = randomize_user_agent
+        self.wait_strategy = wait_strategy
+        self.max_request_attempts = max_request_attempts
+
+        logger.debug(f"Scraper initialized with client: {self.client}")
+
+    def set_user_agent(self, user_agent: str) -> None:
+        self.client.headers["User-Agent"] = user_agent
+        logger.debug(f"User-Agent client header set to: '{user_agent}'")
+
+    def set_no_script(self, no_script: bool) -> None:
+        value = "1" if no_script else "0"
+        self.client.cookies.set("noscript", value)
+        logger.debug(f"NoScript (noscript) client cookie set to: '{value}'")
+
+    def fetch_category(
+            self,
+            url: str,
+            category_type: Type[Category] = Yad2Category,
+            params: Optional[QueryParamTypes] = None
+    ) -> Category:
+        logger.debug(f"Fetching category from URL: '{url}'")
+        response = self.get(url, params)
+        logger.debug(f"Category fetched successfully from URL: '{url}'")
+        return category_type.from_html_io(response)
+
+    def get(self, url: str, params: Optional[QueryParamTypes] = None) -> httpx.Response:
+        return self.request("GET", url, params=params)
+
+    def request(self, method: str, url: str, params: Optional[QueryParamTypes] = None) -> httpx.Response:
+        if not isinstance(self.max_request_attempts, int):
+            raise TypeError(f"max_request_attempts must be of type 'int', but got {type(self.max_request_attempts)}")
+
+        if self.max_request_attempts <= 0:
+            raise ValueError(f"max_request_attempts must be a positive integer, but got {self.max_request_attempts}")
+
+        request_options = self._prepare_request_options(params=params)
+        error_list = []
+
+        for attempt in range(1, self.max_request_attempts + 1):
+            try:
+                return self._send_request(method, url, request_options, attempt)
+            except Exception as error:
+                logger.error(f"{method} request to '{url}' failed {self._format_attempt_info(attempt)}: {error}")
+                error_list.append(error)
+
+        if self.max_request_attempts == 1:
+            raise error_list[0]  # only one error exists, raise it
+
+        max_attempts_error = MaxRequestAttemptsExceededError(method, url, self.max_request_attempts, error_list)
+        logger.error(str(max_attempts_error))
+        raise max_attempts_error from error_list[-1]  # multiple errors exist, raise from the last one
+
+    def close(self) -> None:
+        logger.debug("Closing scraper client")
+        self.client.close()
+        logger.info("Scraper client closed")
+
+    def _send_request(self, method: str, url: str, request_options: Dict[str, Any], attempt: int) -> httpx.Response:
+        if self.randomize_user_agent:
+            self._set_random_user_agent(request_options)
+
+        if self.wait_strategy:
+            self._apply_wait_strategy(attempt)
+
+        logger.info(f"Sending {method} request to URL: '{url}' {self._format_attempt_info(attempt)}")
+        response = self.client.request(method, url, **request_options)
+        logger.debug(f"Received response {response.status_code} from '{url}' {self._format_attempt_info(attempt)}")
+        self._validate_response(response)
+
+        return response
+
+    def _prepare_request_options(self, params: Optional[QueryParamTypes] = None) -> Dict[str, Any]:
+        logger.debug("Preparing request options from defaults")
+        request_options = self.request_defaults.copy()
+
+        if params:
+            request_options.setdefault("params", {}).update(params)
+            logger.debug(f"Updated request options with query params: {params}")
+
+        return request_options
+
+    @staticmethod
+    def _set_random_user_agent(request_options: Dict[str, str]):
+        user_agent = fua.random
+        request_options.setdefault("headers", {})["User-Agent"] = user_agent
+        logger.debug(f"Updated request options with random User-Agent header: '{user_agent}'")
+
+    def _apply_wait_strategy(self, attempt: int):
+        wait_time = self.wait_strategy(attempt)
+        if not wait_time:
+            return
+
+        logger.debug(f"Waiting {wait_time:.2f} seconds before request {self._format_attempt_info(attempt)}")
+        time.sleep(wait_time)
+
+    @staticmethod
+    def _validate_response(response: httpx.Response):
+        response.raise_for_status()
+
+        if ANTIBOT_CONTENT_IDENTIFIER in response.content:
+            raise AntiBotDetectedError(
+                f"The response contains Anti-Bot content",
+                request=response.request,
+                response=response
+            )
+        if response.request.method == "GET" and PAGE_CONTENT_IDENTIFIER not in response.content:
+            raise UnexpectedContentError(
+                "The GET response does not contain yad2 related content",
+                request=response.request,
+                response=response
+            )
+
+        logger.debug("Response validation succeeded")
+
+    def _format_attempt_info(self, attempt: int) -> str:
+        return f"(attempt {attempt}/{self.max_request_attempts})"
+
+    def __enter__(self):
+        logger.debug("Entering scraper context")
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        logger.debug("Exiting scraper context")
+        self.close()

{yad2_scraper-0.2.0 → yad2_scraper-0.4.0}/yad2_scraper/utils.py

@@ -1,17 +1,6 @@
-import httpx
-from fake_useragent import FakeUserAgent
 from bs4 import BeautifulSoup, Tag
 from typing import Union, List
 
-from yad2_scraper.exceptions import AntiBotDetectedError
-from yad2_scraper.constants import ANTIBOT_CONTENT
-
-fua = FakeUserAgent()
-
-
-def get_random_user_agent() -> str:
-    return fua.random
-
 
 def join_url(url: str, path: str) -> str:
     return url.rstrip("/") + "/" + path.lstrip("/")
@@ -24,13 +13,6 @@ def get_parent_url(url: str) -> str:
     return url.rstrip("/").rsplit("/", 1)[0]
 
 
-def validate_http_response(response: httpx.Response):
-    response.raise_for_status()
-
-    if ANTIBOT_CONTENT in response.content:
-        raise AntiBotDetectedError(f"The response contains Anti-Bot content")
-
-
 def find_html_tag_by_class_substring(e: Union[BeautifulSoup, Tag], tag_name: str, substring: str) -> Tag:
     return e.find(tag_name, class_=lambda class_name: class_name and substring in class_name)
 

yad2_scraper-0.2.0/yad2_scraper/exceptions.py

@@ -1,2 +0,0 @@
-class AntiBotDetectedError(Exception):
-    pass

yad2_scraper-0.2.0/yad2_scraper/scraper.py

@@ -1,107 +0,0 @@
-import logging
-import httpx
-import time
-import random
-from typing import Optional, Dict, Any, Tuple, Union, Type, TypeVar
-
-from yad2_scraper.category import Yad2Category
-from yad2_scraper.query import QueryFilters
-from yad2_scraper.utils import get_random_user_agent, validate_http_response
-from yad2_scraper.constants import (
-    DEFAULT_REQUEST_HEADERS,
-    ALLOW_REQUEST_REDIRECTS,
-    VERIFY_REQUEST_SSL
-)
-
-Category = TypeVar("Category", bound=Yad2Category)
-DelayRange = Tuple[float, float]
-QueryParams = Union[QueryFilters, Dict[str, Any]]
-
-logger = logging.getLogger(__name__)
-
-
-class Yad2Scraper:
-    def __init__(
-            self,
-            session: Optional[httpx.Client] = None,
-            request_kwargs: Dict[str, Any] = None,
-            randomize_user_agent: bool = False,
-            requests_delay_range: Optional[DelayRange] = None,
-    ):
-        self.session = session or httpx.Client(
-            headers=DEFAULT_REQUEST_HEADERS,
-            follow_redirects=ALLOW_REQUEST_REDIRECTS,
-            verify=VERIFY_REQUEST_SSL
-        )
-        self.request_kwargs = request_kwargs or {}
-        self.randomize_user_agent = randomize_user_agent
-        self.requests_delay_range = requests_delay_range
-
-        logger.debug(f"Initialized with session {self.session} and request kwargs: {self.request_kwargs}")
-
-    def set_user_agent(self, user_agent: str):
-        self.session.headers["User-Agent"] = user_agent
-        logger.debug(f"User-Agent session header set to: '{user_agent}'")
-
-    def set_no_script(self, no_script: bool):
-        value = "1" if no_script else "0"  # str(int(no_script))
-        self.session.cookies.set("noscript", value)
-        logger.debug(f"NoScript session cookie set to: '{value}'")
-
-    def fetch_category(
-            self,
-            url: str,
-            query_params: Optional[QueryParams] = None,
-            category_type: Type[Category] = Yad2Category
-    ) -> Category:
-        logger.debug(f"Fetching category from URL: '{url}'")
-        response = self.get(url, query_params)
-        logger.debug(f"Category fetched successfully from URL: '{url}'")
-        return category_type.from_html_io(response)
-
-    def get(self, url: str, query_params: Optional[QueryParams] = None) -> httpx.Response:
-        return self.request("GET", url, query_params=query_params)
-
-    def request(self, method: str, url: str, query_params: Optional[QueryParams] = None) -> httpx.Response:
-        request_kwargs = self._prepare_request_kwargs(query_params=query_params)
-
-        if self.requests_delay_range:
-            self._apply_request_delay()
-
-        try:
-            logger.info(f"Making {method} request to URL: '{url}'")  # request kwargs not logged - may be sensitive
-            response = self.session.request(method, url, **request_kwargs)
-            logger.debug(f"Received response with status code: {response.status_code}")
-
-            validate_http_response(response)
-            logger.debug("Response validation succeeded")
-        except Exception as error:
-            logger.error(f"Request to '{url}' failed: {error}")
-            raise error
-
-        return response
-
-    def _prepare_request_kwargs(self, query_params: Optional[QueryParams] = None) -> Dict[str, Any]:
-        logger.debug("Preparing request kwargs from defaults")
-        request_kwargs = self.request_kwargs.copy()
-
-        if query_params:
-            request_kwargs.setdefault("params", {}).update(query_params)
-            logger.debug(f"Updated request kwargs with query params: {query_params}")
-
-        if self.randomize_user_agent:
-            random_user_agent = get_random_user_agent()
-            request_kwargs.setdefault("headers", {})["User-Agent"] = random_user_agent
-            logger.debug(f"Updated request kwargs with random 'User-Agent' header: '{random_user_agent}'")
-
-        return request_kwargs
-
-    def _apply_request_delay(self):
-        delay = random.uniform(*self.requests_delay_range)
-        logger.debug(f"Applying request delay of {delay:.2f} seconds")
-        time.sleep(delay)
-
-    def close(self):
-        logger.debug("Closing scraper session")
-        self.session.close()
-        logger.info("Scraper session closed")