mcmaster_scraper.sync_api

View Source

 1from pandas import DataFrame
 2
 3from . import async_api
 4from ._utils.event_loop_wrapper import run_in_loop_sync
 5
 6
 7def get_products_from_url(url: str, refresh: bool = False) -> DataFrame:
 8    """Gets product tables from a McMaster-Carr URL.
 9
10    If there are multiple product tables, they will be merged,
11    and an additional "Product Type" column will be added.
12
13    Parameters
14    ----------
15    url : str
16        The URL to scrape.
17        Must be a valid McMaster-Carr URL.
18        The product tables must be visible on the webpage.
19    refresh : bool, default False
20        Whether to refresh the cached data. Default is False.
21
22    Returns
23    -------
24    DataFrame
25        A pandas DataFrame containing the combined product tables.
26
27    Raises
28    ------
29    ValueError
30        If the URL is not a valid McMaster-Carr URL.
31    UnsupportedOperation
32        If product table extraction is unsupported for the URL.
33    """
34    return run_in_loop_sync(async_api.get_products_from_url(url, refresh))
35
36
37def get_products_from_urls(urls: list[str], refresh: bool = False) -> list[DataFrame]:
38    """Gets product tables from a list of McMaster-Carr URLs.
39
40    See Also
41    --------
42    get_products_from_url
43    """
44    return run_in_loop_sync(async_api.get_products_from_urls(urls, refresh))

def get_products_from_url(url: str, refresh: bool = False) -> pandas.DataFrame: View Source

 8def get_products_from_url(url: str, refresh: bool = False) -> DataFrame:
 9    """Gets product tables from a McMaster-Carr URL.
10
11    If there are multiple product tables, they will be merged,
12    and an additional "Product Type" column will be added.
13
14    Parameters
15    ----------
16    url : str
17        The URL to scrape.
18        Must be a valid McMaster-Carr URL.
19        The product tables must be visible on the webpage.
20    refresh : bool, default False
21        Whether to refresh the cached data. Default is False.
22
23    Returns
24    -------
25    DataFrame
26        A pandas DataFrame containing the combined product tables.
27
28    Raises
29    ------
30    ValueError
31        If the URL is not a valid McMaster-Carr URL.
32    UnsupportedOperation
33        If product table extraction is unsupported for the URL.
34    """
35    return run_in_loop_sync(async_api.get_products_from_url(url, refresh))

Gets product tables from a McMaster-Carr URL.

If there are multiple product tables, they will be merged, and an additional "Product Type" column will be added.

Parameters

url (str): The URL to scrape. Must be a valid McMaster-Carr URL. The product tables must be visible on the webpage.
refresh (bool, default False): Whether to refresh the cached data. Default is False.

Returns

DataFrame: A pandas DataFrame containing the combined product tables.

Raises

ValueError: If the URL is not a valid McMaster-Carr URL.
UnsupportedOperation: If product table extraction is unsupported for the URL.

def get_products_from_urls(urls: list[str], refresh: bool = False) -> list[pandas.DataFrame]: View Source

38def get_products_from_urls(urls: list[str], refresh: bool = False) -> list[DataFrame]:
39    """Gets product tables from a list of McMaster-Carr URLs.
40
41    See Also
42    --------
43    get_products_from_url
44    """
45    return run_in_loop_sync(async_api.get_products_from_urls(urls, refresh))

Gets product tables from a list of McMaster-Carr URLs.