Python，漂亮湯，如何提取數據並打印到CSV文件

Question

因此，我已經為此工作了一段時間，但似乎無法找到答案或想出辦法。 因此，我正在從Steam中提取數據，我需要弄清楚如何獲取平台（例如mac）並將其轉換為數字（字符串編號）。 例如，如果游戲支持mac，它將在我的列表中顯示為“ 1”，但如果不支持，則它將顯示為“ 0”。 我遇到的問題是代碼僅運行一次並將其全部設置為“ 1”。

from urllib.request import urlopen as uReq
from bs4 import BeautifulSoup as soup
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import re
from datetime import timedelta
import datetime
import time
import csv
my_url = 'https://store.steampowered.com/search/?specials=1&page=1'

#opening up connectin, grabbing the page
uClient = uReq(my_url)
page_html = uClient.read()
uClient.close()

#html parsing
page_soup = soup(page_html, "html.parser")

#grab products
containers = page_soup.findAll("div", {"class":"responsive_search_name_combined"})

filename = "products.csv"
f = open(filename, "w", encoding='UTF-8')
headers = "Titles, Release_date, Discount, Price before, Price after, Positive review, Reviewers, Win, Lin, Osx, Time \n"
f.write(headers)
#f.write(headers)
#len(containers)
#containers[1]
ts = time.time()
st = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d %H:%M:%S')
print(st)

for container in containers:
    titles_container = container.findAll("span",{"class":"title"})
    titl = titles_container[0].text
    print(titl)

    product_container = container.findAll("div",{"class":"search_released"})
    product_date = product_container[0].text
    print(product_date)

    product_discount_container = container.findAll("div",{"class":"search_discount"})
    product_discount = product_discount_container[0].text
    print(product_discount)

    product_price_container_before = container.findAll("div",{"class":"search_price"})
    product_price_before = product_price_container_before[0].text
    test = re.findall('(\d+\W)',product_price_before)
    testing = test[0] + test[1]
    print(testing)

    product_price_container_after = container.findAll("div",{"class":"discounted"})
    for product_price_after in product_price_container_after:
        product_price_after.find("span").extract()
        print(product_price_after.text)

    product_review_container = container.findAll("span",{"class":"search_review_summary"})
    for product_review in product_review_container:
        prr = product_review.get('data-tooltip-html')
        a = re.findall('(\d+%)|(\d+\d+)',prr)
        c = a[1][1]
        print(c)


    product_platform_container = container.findAll("span",{"class":"platform_img"})
    for product_platform in product_platform_container:
        platform = product_platform.get('class')[1]
        platt = re.findall('(\Aw)',platform)
        plattt = re.findall('(\Am)',platform)
        platttt = re.findall('(\Al)',platform)
        print(platt)
        print(plattt)
        print(platttt)

        for p in plattt:
            if "m" in p:
                macken = "1"    
            elif "m" not in p:
                macken = "0"
            print(macken)


    f.write(titl + "," + product_date.replace(",","") + "," + product_discount.replace("\n", "") + "," + testing.replace(",", ".") + "," + product_price_after.text.replace("\n","").replace(" ", "").replace(",",".").replace("\t\t\t\t\t\t\t","") + "," + a[0][0] + "," + c.replace(",","") + "," + y + "," + macken + "," + "blah" + "," + st + "\n")

f.close()
pd.read_csv("products.csv", error_bad_lines=False)

我也將其寫到csv文件中。 因此，當我將其寫入csv文件時，只需說1、1、1、1、1 ...

我正在從以下頁面獲取數據： “ https://store.steampowered.com/search/?specials=1&page=1”

我知道這個問題有點令人困惑，因此希望您能提供幫助，如果您需要更多代碼，請告訴我。

Answer 1

您的陳述有誤，這就是為什么您得到1，請參見下面的代碼！

import requests,csv
from bs4 import BeautifulSoup


req = requests.get('https://store.steampowered.com/search/?specials=1&page=1')
soup = BeautifulSoup(req.content,'html.parser')
data = []
for platform in soup.find_all('div', attrs={'class':'col search_name ellipsis'}):
    title = platform.find('span',attrs={'class':'title'}).text
    if platform.find('span',attrs={'class':'win'}):
        win = '1'
    else:
        win = '0'

    if platform.find('span',attrs={'class':'mac'}):
        mac = '1'
    else:
        mac = '0'

    if platform.find('span',attrs={'class':'linux'}):
        linux = '1'
    else:
        linux = '0'

    data.append({
        'title':title.encode('utf-8'),
        'win':win,
        'mac':mac,
        'linux':linux})

with open('data.csv', 'w', newline='') as f:
    fields = ['title','win','mac','linux']
    writer = csv.DictWriter(f, fieldnames=fields)
    writer.writeheader()
    writer.writerows(data) 

Answer 2

這是我的方法：

import csv

# ...

rows = []
product_platform_container = container.findAll("span",{"class":"platform_img"})
for product_platform in product_platform_container:
    platform = product_platform.get('class')[1]
    win_p = re.findall('(\Aw)',platform)
    mac_p = re.findall('(\Am)',platform)
    linux_p = re.findall('(\Al)',platform)
    print(win_p)
    print(mac_p)
    print(linux_p)
    row = {
       "linux": 1 if linux_p else 0,
       "win": 1 if win_p else 0,
       "mac": 1 if mac_p else 0
    }
    rows.append(row)

# After you parsed all entries...
fieldnames = ['mac', 'win', 'linux']
writer = csv.DictWriter(f, fieldnames=fieldnames)

writer.writeheader()
for row in rows:
    writer.writerow(row)

說明 ：在用re標識平台后，我們創建了csv行，其中僅當mac ， win和linux的對應匹配項（ mac_p ， win_p和linux_p ）不為空時，才會有1。 f是打開的文件對象。 查看這篇文章，其中顯示了如何在python中使用csv文件。