python中csv文件中循环的输出

在这个脚本中，我必须解析一些URL并将输出打印到CSV文件中

import requests
import CSV
from urllib.parse import urlparse

with open(r'C:\Users\acer\Desktop\Project\WordPress\output.csv', 'w', newline='') as file: ==>doubt
    writer = csv.writer(file)                                                              ==>doubt
def content_length(domain):
    try:
        r = requests.get(domain.strip())
        surl = r.url
        urlp = urlparse(surl)
        furl = urlp.scheme + '://' + urlp.hostname + '/'
        rd = requests.get(furl.strip())
        rdstat = rd.status_code
        #print(rdstat)
        if rd.status_code == 403:
            rdmsg = '403 - Forbidden'
        elif rd.status_code == 200:
            r1 = requests.get(furl, stream = True)
            c_length = r1.headers['content-length']
            rdmsg = c_length
        else:
            rdmsg = 'Not Available'
            #print (rdmsg)
        final_print = str(rdstat) + (',') + rdmsg
        print(final_print)
        writer.writerow(["Source Url", "Final Url", "Status Code", "Content-Length"])  ==>doubt
        writer.writerow([surl,furl,str(rdstat),rdmsg])                                 ==>doubt

    except Exception as e:
        print(domain.strip() + ',' + 'Exception')
        print(e)


print('Response Status Code,Content Length')





with open(r'C:\Users\acer\Desktop\Project\WordPress\domains.txt', 'r') as domlist:
    for dom in domlist:
        content_length(dom)

---

在这里，我的问题是我必须为每次迭代（即文本文件中的每个url）在CSV文件中添加输出。但是，我不知道在哪里添加CSV的代码段

您可以尝试重新构造代码，这样就不用先发出一个请求，然后再写一行；尝试发出所有请求，将数据放入列表，然后将这些列表写入csv文件

您可以通过返回数据而不是将其写入

content\u length

函数来完成此操作：

def content_length(domain):
    try:
        r = requests.get(domain.strip())
        surl = r.url
        urlp = urlparse(surl)
        furl = urlp.scheme + '://' + urlp.hostname + '/'
        rd = requests.get(furl.strip())
        rdstat = rd.status_code
        #print(rdstat)
        if rd.status_code == 403:
            rdmsg = '403 - Forbidden'
        elif rd.status_code == 200:
            r1 = requests.get(furl, stream = True)
            c_length = r1.headers['content-length']
            rdmsg = c_length
        else:
            rdmsg = 'Not Available'
            #print (rdmsg)
        final_print = str(rdstat) + (',') + rdmsg
        print(final_print)
        return [surl,furl,str(rdstat),rdmsg]

    except Exception as e:
        print(domain.strip() + ',' + 'Exception')
        print(e)

这将返回一个列表，该列表将是您要写入的行。现在，您需要另一个函数从域文件中获取所有“行”：

def all_domains():
    dom_data = []
    with open(r'C:\Users\acer\Desktop\Project\WordPress\domains.txt', 'r') as file:
        domlist = file.readlines()
        for dom in domlist:
            cl = content_length(dom)
            dom_data.append(cl)
    return dom_data

现在，您可以使用

write\u rows

将

所有\u域的结果写入csv：

domains = all_domains()
with open(r'C:\Users\acer\Desktop\Project\WordPress\output.csv', 'w', newline='') as file:
    writer = csv.writer(file)
    # Write headers
    writer.writerow(["Source Url", "Final Url", "Status Code", "Content-Length"])
    # Write domains
    writer.writerows(domains)

此外，当您导入文件顶部的
csv
包时，请确保该文件是小写而不是大写的“csv”，因为这将引发豁免

希望这有帮助