在csv文件中添加一个静态标题，用一个单词填充所有行

Question

我正在收集名称和数字，并将其导出到csv文件中。

列A=名称B列=数字

如何使列c用"0"填充所有行；Phoenix"；所以每一个有名字或数字的列c都会说phoenix？

import csv
import requests
from bs4 import BeautifulSoup

realtor_data = []
for page in range(1, 6):
print(f"Scraping page {page}...")
url = f"https://www.realtor.com/realestateagents/phoenix_az/pg-{page}"
soup = BeautifulSoup(requests.get(url).text, "html.parser")
for agent_card in soup.find_all("div", {"class": "agent-list-card clearfix"}):
name = agent_card.find("div", {"class": "agent-name text-bold"}).find("a")
number = agent_card.find("div", {"itemprop": "telephone"})
realtor_data.append(
[
name.getText().strip(),
number.getText().strip() if number is not None else "N/A"

],
)
with open("data.csv", "w") as output:
w = csv.writer(output)
w.writerow(["NAME:", "PHONE NUMBER:", "CITY:"])
w.writerows(realtor_data)

Answer 1

有带phoenix的c列。

import csv
import requests
from bs4 import BeautifulSoup

realtor_data = []
for page in range(1, 6):
print(f"Scraping page {page}...")
url = f"https://www.realtor.com/realestateagents/phoenix_az/pg-{page}"
soup = BeautifulSoup(requests.get(url).text, "html.parser")
for agent_card in soup.find_all("div", {"class": "agent-list-card clearfix"}):
name = agent_card.find("div", {"class": "agent-name text-bold"}).find("a")
number = agent_card.find("div", {"itemprop": "telephone"})
realtor_data.append(
[
name.getText().strip(),
number.getText().strip() if number is not None else "N/A"

],
)
with open("data.csv", "w") as output:
w = csv.writer(output)
w.writerow(["NAME:", "PHONE NUMBER:", "CITY:"])
w.writerows(realtor_data)
import pandas as pd
a=pd.read_csv("data.csv")
a2 = a.iloc[:,[0,1]]
a3 = a.iloc[:,[2]]
a3 = a3.fillna("phoenix")
b=pd.concat([a2,a3],axis=1)
b.to_csv("data.csv")

Answer 2

因此，您可以对代码执行此操作，以使所有代码都具有凤凰城：

import csv
import requests
from bs4 import BeautifulSoup

realtor_data = []
for page in range(1, 6):
print(f"Scraping page {page}...")
url = f"https://www.realtor.com/realestateagents/phoenix_az/pg-{page}"
soup = BeautifulSoup(requests.get(url).text, "html.parser")
for agent_card in soup.find_all("div", {"class": "agent-list-card clearfix"}):
name = agent_card.find("div", {"class": "agent-name text-bold"}).find("a")
number = agent_card.find("div", {"itemprop": "telephone"})
data_list = []
if name:
data_list.append(name.getText().strip())
else:
data_list.append("N/A")
if number:
data_list.append(number.getText().strip())
else:
data_list.append("N/A")
data_list.append('Phoenix')
realtor_data.append(data_list)
with open("data.csv", "w") as output:
w = csv.writer(output)
w.writerow(["NAME:", "PHONE NUMBER:", "CITY:"])
w.writerows(realtor_data)

你可能想看看熊猫。DataFrame对象，并在其中附加一个包含每个字段值的字典，因为这将使访问数据变得更容易，而不是遍历csv文件。

*经过编辑以确保即使您没有有效的编号或名称，行中也始终有3个项目，并更改了一行if else语法