def run(self):
print(f"{self.name} start...")
start = time.time()
file_path = f"{self.dir_name}\\{utils.now_timestamp()}-{self.name}.xlsx"
# 创建空Excel并写入表头
utils.create_xlsx_with_head(file_path=file_path, sheet_name='+'.join(self.keywords))
start_crawl(file_path, self.keywords, self.start_time, self.end_time)
end = time.time()
print(f"{self.name} end, totals:{TOTALS}, used:{round((end - start) / 60, 2)} min")
class Task(threading.Thread):
def __init__(self, thread_id, name, dir_name, keywords, start_time, end_time):
threading.Thread.__init__(self)
self.thread_id = thread_id
self.name = name
self.dir_name = dir_name
self.keywords = keywords
self.start_time = start_time
self.end_time = end_time
def run(self):
print(f"{self.name} start...")
start = time.time()
file_path = f"{self.dir_name}\\{utils.now_timestamp()}-{self.name}.xlsx"
# 创建空Excel并写入表头
utils.create_xlsx_with_head(file_path=file_path, sheet_name='+'.join(self.keywords))
start_crawl(file_path, self.keywords, self.start_time, self.end_time)
end = time.time()
print(f"{self.name} end, totals:{TOTALS}, used:{round((end - start) / 60, 2)} min")
if __name__ == '__main__':
keywords = ["China", "Threat"]
start_time = "20210525"
end_time = "20210530"
# 创建空Excel并写入表头
utils.create_xlsx_with_head("./WSJ.xlsx", sheet_name='+'.join(keywords))
start_crawl("./WSJ.xlsx", keywords=keywords, start_time=start_time, end_time=end_time)
def save_to_excel(file_path, keywords, item_set):
# 创建空Excel并写入表头
utils.create_xlsx_with_head(file_path=file_path,
sheet_name='+'.join(keywords))
# 写入数据
utils.write_xlsx_apend(file_path, item_set)
