0

我正在尝试使用它的 python 库 pyral 来获取 Rally 数据。顺序相同的代码可以工作，但速度很慢。我想过使用 python 多进程包，但是我的 pool.apply 方法被卡住并且永远不会执行。我尝试在 Pycharm IDE 以及 windows cmd 提示符下运行它。

import pandas as pd
from pyral import Rally
from multiprocessing import Pool, Manager
from pyral.entity import Project


def process_row(sheetHeaders: list, item: Project, L: list):
    print('processing row : ' + item.Name)  ## this print never gets called
    row = ()
    for header in sheetHeaders:
        row.append(process_cell(header, item))
    L.append(row)


def process_cell(attr, item: Project):
    param = getattr(item, attr)
    if param is None:
        return None
    try:
        if attr == 'Owner':
            return param.__getattr__('Name')
        elif attr == 'Parent':
            return param.__getattr__('ObjectID')
        else:
            return param
    except KeyError as e:
        print(e)

# Projects
# PortfolioItem
# User Story
# Hierarchical Req
# tasks
# defects

# -------------MAIN-----------------


def main():
    # Rally connection
    rally = Rally('rally1.rallydev.com', apikey='<my_key>')
    file = 'rally_data.xlsx'
    headers = {
        'Project': ['Name', 'Description', 'CreationDate', 'ObjectID', 'Parent', 'Owner', 'State'],
    }
    sheetName = 'Project'
    sheetHeaders = headers.get(sheetName)
    p = Pool(1)
    result = rally.get(sheetName, fetch=True, pagesize=10)
    with Manager() as manager:
        L = manager.list()
        for item in result:
            print('adding row for : ' + item.Name)
            p.apply_async(func=process_row, args=(sheetHeaders, item, L)) ## gets stuck here
        p.close()
        p.join()
        pd.DataFrame(L).to_excel(file, sheet_name=sheetName)


if __name__ == '__main__':
    main()

也试过没有经理列表，结果没有任何差异


def main():
    # Rally connection
    rally = Rally('rally1.rallydev.com', apikey='<key>')
    file = 'rally_data.xlsx'
    headers = {
        'Project': ['Name', 'Description', 'CreationDate', 'ObjectID', 'Parent', 'Owner', 'State'],
    }
    sheetName = 'Project'
    sheetHeaders = headers.get(sheetName)
    result = rally.get(sheetName, fetch=True, pagesize=10)
    async_results = []
    with Pool(50) as p:
        for item in result:
            print('adding row for : ' + item.Name)
            async_results.append(p.apply_async(func=process_row, args=(sheetHeaders, item)))
    res = [r.get() for r in async_results]
    pd.DataFrame(res).to_excel(file, sheet_name=sheetName)
4

0 回答 0