yad2-scraper 0.3.0__tar.gz → 0.4.0__tar.gz

{yad2_scraper-0.3.0 → yad2_scraper-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: yad2-scraper
-Version: 0.3.0
+Version: 0.4.0
 Summary: Scrape Yad2 in Python.
 License: LICENSE
 Author: dav ost

{yad2_scraper-0.3.0 → yad2_scraper-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "yad2-scraper"
-version = "0.3.0"
+version = "0.4.0"
 description = "Scrape Yad2 in Python."
 authors = ["dav ost <davidost2003@gmail.com>"]
 license = "LICENSE"

{yad2_scraper-0.3.0 → yad2_scraper-0.4.0}/yad2_scraper/constants.py

@@ -19,7 +19,7 @@ ALLOW_REQUEST_REDIRECTS = True
 VERIFY_REQUEST_SSL = True
 
 ANTIBOT_CONTENT_IDENTIFIER = b"Are you for real"  # robot-captcha
-YAD2_CONTENT_IDENTIFIER = b"https://www.yad2.co.il/"
+PAGE_CONTENT_IDENTIFIER = b"https://www.yad2.co.il/"
 
 FIRST_PAGE_NUMBER = 1
 NOT_MENTIONED_PRICE_RANGE = 0, 0

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-0.3.0 → yad2_scraper-0.4.0}/yad2_scraper/scraper.py

@@ -1,25 +1,25 @@
 import logging
 import httpx
 import time
-import random
-from typing import Optional, Dict, Any, Tuple, Union, Type, TypeVar
+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.utils import get_random_user_agent
-from yad2_scraper.exceptions import AntiBotDetectedError, UnexpectedContentError, MaxRequestRetriesExceededError
+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,
-    YAD2_CONTENT_IDENTIFIER
+    PAGE_CONTENT_IDENTIFIER
 )
 
 Category = TypeVar("Category", bound=Yad2Category)
-DelayRange = Tuple[float, float]
+WaitStrategy = Callable[[int], Optional[float]]
 QueryParamTypes = Union[QueryFilters, Dict[str, Any]]
 
+fua = FakeUserAgent()
 logger = logging.getLogger(__name__)
 
 
@@ -28,9 +28,9 @@ class Yad2Scraper:
             self,
             client: Optional[httpx.Client] = None,
             request_defaults: Optional[Dict[str, Any]] = None,
-            randomize_user_agent: bool = False,
-            random_delay_range: Optional[DelayRange] = None,
-            max_retries: int = 0
+            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,
@@ -39,16 +39,25 @@ class Yad2Scraper:
         )
         self.request_defaults = request_defaults or {}
         self.randomize_user_agent = randomize_user_agent
-        self.random_delay_range = random_delay_range
-        self.max_retries = max_retries
+        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,
-            params: Optional[QueryParamTypes] = None,
-            category_type: Type[Category] = Yad2Category
+            category_type: Type[Category] = Yad2Category,
+            params: Optional[QueryParamTypes] = None
     ) -> Category:
         logger.debug(f"Fetching category from URL: '{url}'")
         response = self.get(url, params)
@@ -59,72 +68,48 @@ class Yad2Scraper:
         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 = []
 
-        try:
-            return self._send_request(method, url, request_options)
-        except Exception as error:
-            return self._handle_request_error(method, url, request_options, error)
+        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)
 
-    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}'")
+        if self.max_request_attempts == 1:
+            raise error_list[0]  # only one error exists, raise it
 
-    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 client cookie set to: '{value}'")
+        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]) -> httpx.Response:
+    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.random_delay_range:
-            self._apply_request_delay()
+        if self.wait_strategy:
+            self._apply_wait_strategy(attempt)
 
-        logger.info(f"Making {method} request to URL: '{url}'")
+        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 with status code: {response.status_code}")
+        logger.debug(f"Received response {response.status_code} from '{url}' {self._format_attempt_info(attempt)}")
         self._validate_response(response)
 
         return response
 
-    def _handle_request_error(
-            self,
-            method: str,
-            url: str,
-            request_options: Dict[str, Any],
-            error: Exception
-    ) -> httpx.Response:
-        logger.error(f"{method} request to '{url}' failed: {error}")
-
-        if self.max_retries == 0:
-            raise error
-
-        return self._retry_request(method, url, request_options)
-
-    def _retry_request(self, method: str, url: str, request_options: Dict[str, Any]) -> httpx.Response:
-        logger.info(f"Retrying {method} request to '{url}' (max retries: {self.max_retries})")
-
-        errors = []
-
-        for retry_attempt in range(1, self.max_retries + 1):
-            try:
-                logger.debug(f"Retry attempt {retry_attempt}/{self.max_retries}")
-                return self._send_request(method, url, request_options)
-            except Exception as error:
-                logger.warning(f"Retry attempt {retry_attempt} failed: {error}")
-                errors.append(error)
-
-        error_to_raise = MaxRequestRetriesExceededError(method, url, self.max_retries, errors)
-        logger.error(str(error_to_raise))
-        raise error_to_raise from errors[-1]
-
     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()
@@ -135,17 +120,20 @@ class Yad2Scraper:
 
         return request_options
 
-    def _apply_request_delay(self):
-        delay = random.uniform(*self.random_delay_range)
-        logger.debug(f"Applying request delay of {delay:.2f} seconds")
-        time.sleep(delay)
-
     @staticmethod
     def _set_random_user_agent(request_options: Dict[str, str]):
-        user_agent = get_random_user_agent()
+        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()
@@ -156,15 +144,18 @@ class Yad2Scraper:
                 request=response.request,
                 response=response
             )
-        if YAD2_CONTENT_IDENTIFIER not in response.content:
+        if response.request.method == "GET" and PAGE_CONTENT_IDENTIFIER not in response.content:
             raise UnexpectedContentError(
-                "The response does not contain yad2 content",
+                "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

{yad2_scraper-0.3.0 → yad2_scraper-0.4.0}/yad2_scraper/utils.py

@@ -1,13 +1,6 @@
-from fake_useragent import FakeUserAgent
 from bs4 import BeautifulSoup, Tag
 from typing import Union, List
 
-fua = FakeUserAgent()
-
-
-def get_random_user_agent() -> str:
-    return fua.random
-
 
 def join_url(url: str, path: str) -> str:
     return url.rstrip("/") + "/" + path.lstrip("/")

yad2_scraper-0.3.0/yad2_scraper/exceptions.py

@@ -1,31 +0,0 @@
-import httpx
-from typing import List
-
-
-class ResponseError(httpx.HTTPStatusError):
-    # This adds the request/response objects to the error
-    pass
-
-
-class AntiBotDetectedError(ResponseError):
-    pass
-
-
-class UnexpectedContentError(ResponseError):
-    pass
-
-
-class MaxRetriesExceededError(Exception):
-    def __init__(self, msg: str, errors: List[Exception] = None):
-        super().__init__(msg)
-        self.errors = errors
-
-
-class MaxRequestRetriesExceededError(MaxRetriesExceededError):
-    def __init__(self, method: str, url: str, max_retries: int, errors: List[Exception] = None):
-        self.method = method
-        self.url = url
-        self.max_retries = max_retries
-
-        msg = f"All {self.max_retries} retry attempts for {self.method} request to '{self.url}' have failed"
-        super().__init__(msg, errors)