Question

我正在尝试检查一行是否已存在。如果没有，则必须在行中写入内容。我的CSV文件始终为空。

# import libraries
import csv
import urllib2
from bs4 import BeautifulSoup

# integer for first article id
articleid = 4449
articles = 4459

while articleid < articles:
    # specify the url and article id
    url = 'http://www.bkfrem.dk/default.asp?vis=nyheder&id='+str(articleid)
    articleid += 1
    # query the website and return the html to the variable
    page = urllib2.urlopen(url)

    # parse the html using beautiful soup and store in variable soup
    soup = BeautifulSoup(page, 'html.parser')

    # create CSV file
    csvfile = csv.writer(open('news.csv', 'a'))

    # take out the <div> of name and get its value and text
    title_box = soup.find('h1', attrs={'style': 'margin-bottom:0px'})
    title = title_box.text.encode('utf-8').strip()
    date_box = soup.find('div', attrs={'style': 'font-style:italic; padding-bottom:10px'})
    date = date_box.text.encode('utf-8').strip()
    articleText_box = soup.find('div', attrs={'class': 'news'})
    articleText = articleText_box.text.encode('utf-8').strip()

    # print the data (encoded) to the CSV file
    with open('news.csv', 'rb') as csvfileO:
        f_reader = csv.reader(csvfileO, delimiter=',')
        for row in f_reader:
            if articleText not in row:
                csvfile.writerow(["Title", "Date", "Text"])
                csvfile.writerow((title, date, articleText))

我做错了什么，因为它是空的？

Answer 1

for row in f_reader:
    if articleText not in
        csvfile.writerow(["Title", "Date", "Text"])
        csvfile.writerow((title, date, articleText))

您有if articleText not in

不是在什么？你应该让它指向要验证的东西。

if articleText not in "Something":
     csvfile.writerow(["Title", "Date", "Text"])
     csvfile.writerow((title, date, articleText))

Python 2.7：如何检查行是否已存在？

1 个答案: