datamarket 0.7.20__tar.gz → 0.8.0__tar.gz

{datamarket-0.7.20 → datamarket-0.8.0}/PKG-INFO

@@ -1,8 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: datamarket
-Version: 0.7.20
+Version: 0.8.0
 Summary: Utilities that integrate advanced scraping knowledge into just one library.
-Home-page: https://datamarket.es
 License: GPL-3.0-or-later
 Author: DataMarket
 Author-email: techsupport@datamarket.es
@@ -22,7 +21,6 @@ Provides-Extra: boto3
 Provides-Extra: chompjs
 Provides-Extra: click
 Provides-Extra: clickhouse-driver
-Provides-Extra: croniter
 Provides-Extra: datetime
 Provides-Extra: demjson3
 Provides-Extra: dnspython
@@ -36,6 +34,7 @@ Provides-Extra: google-api-python-client
 Provides-Extra: google-auth-httplib2
 Provides-Extra: google-auth-oauthlib
 Provides-Extra: html2text
+Provides-Extra: httpx
 Provides-Extra: json5
 Provides-Extra: lxml
 Provides-Extra: nodriver
@@ -43,7 +42,6 @@ Provides-Extra: openpyxl
 Provides-Extra: pandas
 Provides-Extra: pandera
 Provides-Extra: peerdb
-Provides-Extra: pendulum
 Provides-Extra: pillow
 Provides-Extra: playwright
 Provides-Extra: playwright-stealth
@@ -70,11 +68,12 @@ Requires-Dist: boto3 (==1.35.53) ; extra == "boto3" or extra == "aws" or extra =
 Requires-Dist: chompjs (==1.3.0) ; extra == "chompjs"
 Requires-Dist: click (==8.1.7) ; extra == "click"
 Requires-Dist: clickhouse-driver (==0.2.9) ; extra == "clickhouse-driver" or extra == "peerdb"
-Requires-Dist: croniter (==3.0.4) ; extra == "croniter"
+Requires-Dist: croniter (==3.0.4)
 Requires-Dist: datetime (==5.5) ; extra == "datetime"
 Requires-Dist: demjson3 (==3.0.6) ; extra == "demjson3"
 Requires-Dist: dnspython (==2.7.0) ; extra == "dnspython"
 Requires-Dist: duckduckgo-search (==6.2.11b1) ; extra == "duckduckgo-search"
+Requires-Dist: dynaconf (==3.2.6)
 Requires-Dist: fake-useragent (==1.5.1) ; extra == "fake-useragent"
 Requires-Dist: geoalchemy2 (==0.15.2) ; extra == "geoalchemy2"
 Requires-Dist: geopandas (==1.0.1) ; extra == "geopandas"
@@ -83,13 +82,15 @@ Requires-Dist: google-api-python-client (==2.151.0) ; extra == "google-api-pytho
 Requires-Dist: google-auth-httplib2 (==0.2.0) ; extra == "google-auth-httplib2"
 Requires-Dist: google-auth-oauthlib (==1.2.1) ; extra == "google-auth-oauthlib"
 Requires-Dist: html2text (==2024.2.26) ; extra == "html2text"
+Requires-Dist: httpx[http2] (==0.28.1) ; extra == "httpx"
+Requires-Dist: jinja2 (==3.1.5)
 Requires-Dist: json5 (==0.9.25) ; extra == "json5"
 Requires-Dist: lxml[html-clean] (==5.3.0) ; extra == "lxml"
 Requires-Dist: nodriver (==0.37) ; extra == "nodriver"
 Requires-Dist: openpyxl (==3.1.5) ; extra == "openpyxl"
 Requires-Dist: pandas (==2.2.3) ; extra == "pandas"
 Requires-Dist: pandera (==0.20.4) ; extra == "pandera"
-Requires-Dist: pendulum (==3.0.0) ; extra == "pendulum"
+Requires-Dist: pendulum (==3.0.0)
 Requires-Dist: pillow (==11.0.0) ; extra == "pillow"
 Requires-Dist: playwright (==1.47.0) ; extra == "playwright"
 Requires-Dist: playwright-stealth (==1.0.6) ; extra == "playwright-stealth"
@@ -114,6 +115,7 @@ Requires-Dist: undetected-chromedriver (==3.5.5) ; extra == "undetected-chromedr
 Requires-Dist: unidecode (==1.3.8) ; extra == "unidecode"
 Requires-Dist: xmltodict (==0.14.2) ; extra == "xmltodict"
 Project-URL: Documentation, https://github.com/Data-Market/datamarket
+Project-URL: Homepage, https://datamarket.es
 Project-URL: Repository, https://github.com/Data-Market/datamarket
 Description-Content-Type: text/markdown
 

{datamarket-0.7.20 → datamarket-0.8.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "datamarket"
-version = "0.7.20"
+version = "0.8.0"
 description = "Utilities that integrate advanced scraping knowledge into just one library."
 authors = ["DataMarket <techsupport@datamarket.es>"]
 license = "GPL-3.0-or-later"
@@ -23,12 +23,15 @@ requests = "2.32.3"
 tenacity = "9.0.0"
 beautifulsoup4 = "4.12.3"
 pre-commit = "4.0.1"
+pendulum = "3.0.0"
+croniter = "3.0.4"
+dynaconf = "3.2.6"
+jinja2 = "3.1.5"
 
 boto3 = { version = "1.35.53", optional = true }
 unidecode = { version = "1.3.8", optional = true }
 lxml = { extras = ["html-clean"], version = "5.3.0", optional = true }
 tqdm = { version = "4.66.6", optional = true }
-pendulum = { version = "3.0.0", optional = true }
 pandas = { version = "2.2.3", optional = true }
 pyarrow = { version = "17.0.0", optional = true }
 pytest = { version = "8.3.3", optional = true }
@@ -36,7 +39,6 @@ playwright = { version = "1.47.0", optional = true }
 playwright-stealth = { version = "1.0.6", optional = true }
 soda-core-postgres = { version = "3.4.1", optional = true }
 fake-useragent = { version = "1.5.1", optional = true }
-croniter = { version = "3.0.4", optional = true }
 pydrive2 = { version = "1.20.0", optional = true }
 clickhouse-driver = { version = "0.2.9", optional = true }
 stem = { version = "1.8.2", optional = true }
@@ -67,13 +69,13 @@ google-auth-httplib2 = { version = "0.2.0", optional = true }
 google-auth-oauthlib = { version = "1.2.1", optional = true }
 dnspython = { version = "2.7.0", optional = true }
 openpyxl = { version = "3.1.5", optional = true }
+httpx = { extras = ["http2"], version = "0.28.1", optional = true }
 
 [tool.poetry.extras]
 boto3 = ["boto3"]
 unidecode = ["unidecode"]
 lxml = ["lxml"]
 tqdm = ["tqdm"]
-pendulum = ["pendulum"]
 pandas = ["pandas"]
 pyarrow = ["pyarrow"]
 pytest = ["pytest"]
@@ -81,7 +83,6 @@ playwright = ["playwright"]
 playwright-stealth = ["playwright-stealth"]
 soda-core-postgres = ["soda-core-postgres"]
 fake-useragent = ["fake-useragent"]
-croniter = ["croniter"]
 pydrive2 = ["pydrive2"]
 clickhouse-driver = ["clickhouse-driver"]
 stem = ["stem"]
@@ -112,6 +113,7 @@ google-auth-httplib2 = ["google-auth-httplib2"]
 google-auth-oauthlib = ["google-auth-oauthlib"]
 dnspython = ["dnspython"]
 openpyxl = ["openpyxl"]
+httpx = ["httpx"]
 
 # Interface groups
 aws = ["boto3"]

{datamarket-0.7.20 → datamarket-0.8.0}/src/datamarket/interfaces/aws.py

@@ -16,16 +16,14 @@ class AWSInterface:
         self.profiles = []
         self.config = config
 
-        for section in self.config.sections():
-            if section.startswith("aws:"):
-                profile_name = section.split(":", 1)[1]
-                self.profiles.append(
-                    {
-                        "profile": profile_name,
-                        "bucket": self.config[section]["bucket"],
-                        "session": boto3.Session(profile_name=profile_name),
-                    }
-                )
+        for profile_name, values in self.config.get("aws", {}).items():
+            self.profiles.append(
+                {
+                    "profile": profile_name,
+                    "bucket": values["bucket"],
+                    "session": boto3.Session(profile_name=profile_name),
+                }
+            )
 
         if not self.profiles:
             logger.warning("No AWS profiles found in config file")

datamarket-0.8.0/src/datamarket/utils/main.py

@@ -0,0 +1,167 @@
+########################################################################################################################
+# IMPORTS
+
+import configparser
+import inspect
+import logging
+import random
+import re
+import shlex
+import shutil
+import subprocess
+import time
+from pathlib import Path
+from typing import Literal, Union
+
+import pendulum
+from croniter import croniter
+from dynaconf import Dynaconf, add_converter
+
+########################################################################################################################
+# FUNCTIONS
+
+logger = logging.getLogger(__name__)
+
+
+def get_granular_date(
+    granularity: Union[Literal["monthly", "biweekly", "weekly", "daily"], str], tz: str = "Europe/Madrid"
+) -> str:
+    """
+    Returns the most recent date based on the given granularity or a custom cron expression.
+
+    Args:
+        granularity: Either a predefined value ("monthly", "biweekly", "weekly") or a custom cron expression.
+        tz: Timezone to use for date calculations (default: "Europe/Madrid").
+
+    Returns:
+        A string representing the most recent date in the format "YYYY-MM-DD".
+
+    Raises:
+        ValueError: If the provided granularity or cron expression is invalid.
+    """
+    now = pendulum.now(tz)
+
+    predefined_patterns = {
+        "monthly": "0 0 1 * *",
+        "biweekly": "0 0 1,15 * *",
+        "weekly": "0 0 * * MON",
+        "daily": "0 0 * * *",
+    }
+
+    cron_pattern = predefined_patterns.get(granularity, granularity)
+
+    try:
+        cron = croniter(cron_pattern, now)
+        return cron.get_prev(pendulum.DateTime).strftime("%Y-%m-%d")
+    except Exception as e:
+        raise ValueError("Invalid cron expression or granularity specified.") from e
+
+
+def read_converter(path_str: str):
+    with open(path_str) as f:
+        return f.read()
+
+
+def get_config(config_file: Path, tz: str = "Europe/Madrid"):
+    if Path(config_file).suffix == "ini":
+        logger.warning("Using legacy INI config reader. Please migrate to TOML")
+        cfg = configparser.RawConfigParser()
+        return cfg.read(config_file)
+
+    add_converter("read", read_converter)
+
+    config = Dynaconf(
+        environments=True,
+        env_switcher="SYSTYPE",
+        vars={
+            "today": get_granular_date("daily", tz),
+            "biweekly_date": get_granular_date("biweekly", tz),
+        },
+    )
+
+    config.load_file(path=config_file)
+    config.load_file(path=Path.home() / config_file.name)
+    return config
+
+
+def get_project_metadata():
+    caller_frame = inspect.stack()[1]
+    current_file_parts = Path(caller_frame.filename).resolve().parts
+    src_index = current_file_parts.index("src")
+    cmd_prefix = "dix vnc run --" if shutil.which("dix") else ""
+    pkg_name = current_file_parts[src_index + 1]
+    env_name = f"{pkg_name}_env"
+    project_path = Path(*current_file_parts[:src_index])
+
+    return {"cmd_prefix": cmd_prefix, "pkg_name": pkg_name, "env_name": env_name, "project_path": project_path}
+
+
+def set_logger(level):
+    log = logging.getLogger()
+    log.setLevel(logging.DEBUG)
+    ch = logging.StreamHandler()
+    ch.setLevel(level.upper())
+    formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+    ch.setFormatter(formatter)
+    log.addHandler(ch)
+
+
+def ban_sleep(max_time, min_time=0):
+    sleep_time = int(random.uniform(min_time, max_time))  # noqa: S311
+    logger.info(f"sleeping for {sleep_time} seconds...")
+    time.sleep(sleep_time)
+
+
+def run_bash_command(command):
+    p = subprocess.Popen(shlex.split(command), stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+
+    text_lines = []
+    for line_b in iter(p.stdout.readline, ""):
+        line_str = line_b.decode().strip()
+
+        if not line_str:
+            break
+
+        logger.info(line_str)
+        text_lines.append(line_str)
+
+    return "\n".join(text_lines)
+
+
+def text_to_int(text):
+    max_int32 = 2147483647
+    parsed_str = re.sub(r"[^\d]", "", text)
+    if parsed_str:
+        num = int(parsed_str)
+    else:
+        return None
+
+    if -max_int32 < num < max_int32:
+        return num
+
+
+def sleep_out_interval(from_h, to_h, tz="Europe/Madrid", seconds=1800):
+    while pendulum.now(tz=tz).hour >= to_h or pendulum.now(tz=tz).hour < from_h:
+        logger.warning("time to sleep and not scrape anything...")
+        ban_sleep(seconds, seconds)
+
+
+def sleep_in_interval(from_h, to_h, tz="Europe/Madrid", seconds=1800):
+    while from_h <= pendulum.now(tz=tz).hour < to_h:
+        logger.warning("time to sleep and not scrape anything...")
+        ban_sleep(seconds, seconds)
+
+
+def parse_field(dict_struct, field_path, format_method=None):
+    if not isinstance(field_path, list):
+        raise ValueError("Argument field_path must be of type list")
+
+    field_value = dict_struct
+    for field in field_path:
+        if isinstance(field_value, dict):
+            field_value = field_value.get(field)
+        elif isinstance(field_value, list):
+            field_value = field_value[field] if len(field_value) > field else None
+        if field_value is None:
+            return None
+    return format_method(field_value) if format_method else field_value

datamarket-0.7.20/src/datamarket/utils/main.py

@@ -1,94 +0,0 @@
-########################################################################################################################
-# IMPORTS
-
-import configparser
-import logging
-import random
-import re
-import shlex
-import subprocess
-import time
-
-import pendulum
-
-########################################################################################################################
-# FUNCTIONS
-
-logger = logging.getLogger(__name__)
-
-
-def get_config(config_path):
-    cfg = configparser.RawConfigParser()
-    cfg.read(config_path)
-    return cfg
-
-
-def set_logger(level):
-    log = logging.getLogger()
-    log.setLevel(logging.DEBUG)
-    ch = logging.StreamHandler()
-    ch.setLevel(level.upper())
-    formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-    ch.setFormatter(formatter)
-    log.addHandler(ch)
-
-
-def ban_sleep(max_time, min_time=0):
-    sleep_time = int(random.uniform(min_time, max_time))
-    logger.info(f"sleeping for {sleep_time} seconds...")
-    time.sleep(sleep_time)
-
-
-def run_bash_command(command):
-    p = subprocess.Popen(shlex.split(command), stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
-
-    text_lines = []
-    for line_b in iter(p.stdout.readline, ""):
-        line_str = line_b.decode().strip()
-
-        if not line_str:
-            break
-
-        logger.info(line_str)
-        text_lines.append(line_str)
-
-    return "\n".join(text_lines)
-
-
-def text_to_int(text):
-    max_int32 = 2147483647
-    parsed_str = re.sub(r"[^\d]", "", text)
-    if parsed_str:
-        num = int(parsed_str)
-    else:
-        return None
-
-    if -max_int32 < num < max_int32:
-        return num
-
-
-def sleep_out_interval(from_h, to_h, tz="Europe/Madrid", seconds=1800):
-    while pendulum.now(tz=tz).hour >= to_h or pendulum.now(tz=tz).hour < from_h:
-        logger.warning("time to sleep and not scrape anything...")
-        ban_sleep(seconds, seconds)
-
-
-def sleep_in_interval(from_h, to_h, tz="Europe/Madrid", seconds=1800):
-    while from_h <= pendulum.now(tz=tz).hour < to_h:
-        logger.warning("time to sleep and not scrape anything...")
-        ban_sleep(seconds, seconds)
-
-
-def parse_field(dict_struct, field_path, format_method=None):
-    if not isinstance(field_path, list):
-        raise ValueError("Argument field_path must be of type list")
-
-    field_value = dict_struct
-    for field in field_path:
-        if isinstance(field_value, dict):
-            field_value = field_value.get(field)
-        elif isinstance(field_value, list):
-            field_value = field_value[field] if len(field_value) > field else None
-        if field_value is None:
-            return None
-    return format_method(field_value) if format_method else field_value