gpt4 book ai didi

python - 使用池追加到数组

转载 作者:太空宇宙 更新时间:2023-11-03 20:32:02 25 4
gpt4 key购买 nike

我正在尝试从soccerway.com 抓取数据,并检查该页面是否是一个已完成的游戏/要玩的游戏,每个实例都写入单独的 csv 文件。我正在运行 10,000 个页面,因此使用 Pools 编写了它。但是,我从追加函数中获取空列表,并且无法向 csv 文件写入任何内容。

我尝试直接写入文件而不是列表附加,但这给出了不完整的文件

import requests
from bs4 import BeautifulSoup
import time
import numpy as np
import uuid
import time
from multiprocessing import Pool
import sys, os

fixturesA = []
linksA = []
statsA = []

def parse(url):
try:
#print(url)
delays = [0.25,0.5,0.75,1]
delay = np.random.choice(delays)
#time.sleep(delay)
#r = requests.get(url)
r = requests.get(url, timeout = 10)
soup = BeautifulSoup(r.content, "html.parser")
teams = soup.findAll('h3', attrs = {'class' : 'thick'})
homeTeam = teams[0].text.strip()
awayTeam = teams[2].text.strip()
middle = teams[1].text.strip()
dds = soup.findAll('dd')
date = dds[1].text.strip()
gameWeek = dds[2].text.strip()
if ':' not in middle:
middle = middle.split(" - ")
homeGoals = 0
awayGoals = 0
homeGoals = middle[0]
try:
awayGoals = middle[1]
except Exception as e:
homeGoals = "-1"
awayGoals = "-1"
matchGoals = int(homeGoals) + int(awayGoals)
if(matchGoals >= 0):
if(int(homeGoals) > 0 and int(awayGoals) > 0):
btts = "y"
else:
btts = "n"
halfTimeScore = dds[4].text.strip().split(" - ")
firstHalfHomeGoals = halfTimeScore[0]
firstHalfAwayConc = halfTimeScore[0]
firstHalfAwayGoals = halfTimeScore[1]
firstHalfHomeConc = halfTimeScore[1]
firstHalfTotalGoals = int(firstHalfHomeGoals) + int(firstHalfAwayGoals)
secondHalfHomeGoals = int(homeGoals) - int(firstHalfHomeGoals)
secondHalfAwayConc = int(homeGoals) - int(firstHalfHomeGoals)
secondHalfAwayGoals = int(awayGoals) - int(firstHalfAwayGoals)
secondHalfHomeConc = int(awayGoals) - int(firstHalfAwayGoals)
secondHalfTotalGoals = matchGoals - firstHalfTotalGoals

homeTeamContainers = soup.findAll('div', attrs = {'class' : 'container left'})
homeTeamStarting = homeTeamContainers[2]
homeTeamBench = homeTeamContainers[3]
homeTeamYellows = len(homeTeamStarting.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/700/img/events/YC.png' })) + len(homeTeamBench.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/699/img/events/YC.png' }))
homeTeamReds = len(homeTeamStarting.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/700/img/events/RC.png' })) + len(homeTeamBench.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/699/img/events/RC.png' }))
homeTeamCards = homeTeamYellows + homeTeamReds

awayTeamContainers = soup.findAll('div', attrs = {'class' : 'container right'})
awayTeamStarting = awayTeamContainers[2]
awayTeamBench = awayTeamContainers[3]
awayTeamYellows = len(awayTeamStarting.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/700/img/events/YC.png' })) + len(awayTeamBench.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/699/img/events/YC.png' }))
awayTeamReds = len(awayTeamStarting.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/700/img/events/RC.png' })) + len(awayTeamBench.findAll('img', attrs = {'src' : 'https://s1.swimg.net/gsmf/699/img/events/RC.png' }))
awayTeamCards = awayTeamYellows + awayTeamReds

matchCards = homeTeamCards + awayTeamCards
try:
iframe = soup.findAll('iframe')
iframeSrc = iframe[1]['src']
url = 'https://us.soccerway.com/' + iframeSrc
c = requests.get(url,timeout = 10)
soupC = BeautifulSoup(c.content, "html.parser")

cornerContainer = soupC.findAll('td', attrs = {'class' : 'legend left value'})
homeCorners = cornerContainer[0].text.strip()
awayCornersConc = homeCorners
cornerContainer = soupC.findAll('td', attrs = {'class' : 'legend right value'})
awayCorners = cornerContainer[0].text.strip()
homeCornersConc = awayCorners
matchCorners = int(homeCorners) + int(awayCorners)

print("Got Score . " + homeTeam + " vs " + awayTeam+" . " + gameWeek )
statsA.append(homeTeam + "," + awayTeam + "," + gameWeek + "," + homeGoals + "," + awayGoals + "," + str(matchGoals) + "," + btts + "," + firstHalfHomeGoals + "," + firstHalfHomeConc + "," + firstHalfAwayGoals + "," + firstHalfAwayConc + "," + str(firstHalfTotalGoals) + "," + str(secondHalfHomeGoals) + "," + str(secondHalfHomeConc) + "," + str(secondHalfAwayGoals) + "," + str(secondHalfAwayConc) + "," + str(secondHalfTotalGoals) + "," + str(homeTeamCards) + "," + str(awayTeamCards) + "," + str(matchCards) + "," + homeCorners + "," + awayCorners + "," + homeCornersConc + "," + awayCornersConc + "," + str(matchCorners)+","+dds[0].text.strip() + "\n")
return None
except Exception as e:
print("Got Score no corners. " + homeTeam + " vs " + awayTeam+" . " + gameWeek + " NO FRAME")
statsA.append(homeTeam + "," + awayTeam + "," + gameWeek + "," + homeGoals + "," + awayGoals + "," + str(matchGoals) + "," + btts + "," + firstHalfHomeGoals + "," + firstHalfHomeConc + "," + firstHalfAwayGoals + "," + firstHalfAwayConc + "," + str(firstHalfTotalGoals) + "," + str(secondHalfHomeGoals) + "," + str(secondHalfHomeConc) + "," + str(secondHalfAwayGoals) + "," + str(secondHalfAwayConc) + "," + str(secondHalfTotalGoals) + "," + str(homeTeamCards) + "," + str(awayTeamCards) + "," + str(matchCards) + "," + "" + "," + "" + "," + "" + "," + "" + "," + ""+","+dds[0].text.strip() + "\n")
return None
else:
fixturesA.append(homeTeam + "," + awayTeam + "," + gameWeek + "," + date + "\n")
linksA.append(url + "\n")
print(homeTeam + " vs " + awayTeam + " at " + middle + " GW:" + gameWeek)
return None
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
print(exc_type, fname, exc_tb.tb_lineno)
linksA.append(url + "\n")
print(url)
return None


stats = open('Statsv2.csv','a',encoding='utf-8')
fixtures = open('fixturesv2.csv','w',encoding='utf-8')

with open('links.txt') as f:
content = f.readlines()
content = [x.strip() for x in content]

links = open('links.txt','w')

if __name__ == '__main__':
start_time = time.time()
p = Pool(20) # Pool tells how many at a time
records = p.map(parse, content)
p.terminate()
p.join()

print("--- %s seconds ---" % (time.time() - start_time))

最佳答案

我假设您运行的是 Windows?那么答案是 Windows 中的多处理会创建副本而不是 fork 。因此,您拥有包含列表的主流程,并且您的工作流程(从池中)拥有自己单独的一组列表。

工作人员很可能正确填写了列表,但主进程中的列表没有获取任何数据,因此保持为空。 worker 们也没有归还任何东西。因此,当您在主进程中写入文件时,您会得到空文件。

解决此问题的一个简单方法是在主进程和工作线程之间创建管道或队列,以允许线程之间进行通信。您还可以使用共享数组,就像它们由多处理类提供的那样,但您需要在创建过程中知道长度。

参见文档:Multiprocessing

关于python - 使用池追加到数组,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/57437873/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com