예제 #1
0
def return_cases_NonResidential(pattern1, pattern2, pattern3, pattern4,
                                pattern5, pattern6, pattern7):
    """
    Function scans the LA Public Health Care website and returns a list of the targetted data information. It's
    particularly designed to capture the Non-Residential data since the title web-page is designed with several indentions
    Input: string variable
    Output: list
    """

    soup_strings = []
    for string in soup.strings:
        soup_strings.append(string)

    maxi = len(soup_strings)
    i = 0
    data_extract = []
    la_cases = []

    while (i <= maxi):
        if ((soup_strings[i] == str(pattern1)) &
            (soup_strings[i + 1] == str(pattern2)) &
            (soup_strings[i + 2] == str(pattern3)) &
            (soup_strings[i + 3] == str(pattern4)) &
            (soup_strings[i + 4] == str(pattern5)) &
            (soup_strings[i + 5] == str(pattern6)) &
            (soup_strings[i + 6] == str(pattern7))):
            length = len(soup_strings[i:])
            start = len(soup_strings) - length
            end = start + length
            stop = 'Total'
            placeholder = str()

            while ((start <= end) & (placeholder != stop)):
                placeholder = soup_strings[start]
                data_extract.append(soup_strings[start])
                start += 1

            data_start, data_end = search_start_end(data_extract)

            for i in range(len(data_extract)):
                if ((i >= data_start) & (i <= data_end)):
                    la_cases.append(data_extract[i])
            break
        i += 1

    del data_extract, i, maxi, data_start, data_end, length

    la_cases = remove_tabs_and_obs(la_cases)

    return la_cases
예제 #2
0
def return_cases(search_input):
    """
    Function scans the LA Public Health Care website and returns a list of the targetted data information
    Input: string variable
    Output: list
    """

    soup_strings = []
    for string in soup.strings:
        soup_strings.append(string)

    maxi = len(soup_strings)
    i = 0
    data_extract = []
    la_cases = []

    while (i <= maxi):
        if (soup_strings[i] == str(search_input)):
            length = len(soup_strings[i:])
            start = len(soup_strings) - length
            end = start + length
            stop = 'Total'
            placeholder = str()

            while ((start <= end) & (placeholder != stop)):
                placeholder = soup_strings[start]
                data_extract.append(soup_strings[start])
                start += 1

            data_start, data_end = search_start_end(data_extract)

            for i in range(len(data_extract)):
                if ((i >= data_start) & (i <= data_end)):
                    la_cases.append(data_extract[i])
            break
        i += 1

    del data_extract, i, maxi, data_start, data_end, length

    la_cases = remove_tabs_and_obs(la_cases)

    return la_cases