快捷導(dǎo)航

利用python 讀寫csv文件

更新時(shí)間：2020年09月10日 09:58:13 作者：新碼農(nóng)

python中有一個(gè)讀寫csv文件的包，直接import csv即可。利用這個(gè)python包可以很方便對(duì)csv文件進(jìn)行操作。

1、讀文件

import csv
 
csv_reader = csv.reader(open("data.file", encoding="utf-8"))
for row in csv_reader:
  print(row)

csv_reader把每一行數(shù)據(jù)轉(zhuǎn)化成了一個(gè)list，list中每個(gè)元素是一個(gè)字符串。

2、寫文件

讀文件時(shí)，我們把csv文件讀入列表中，寫文件時(shí)會(huì)把列表中的元素寫入到csv文件中。

list = ["1", "2", "3", "4"]
out = open(outfile, "w")
csv_writer = csv.writer(out)
csv_writer.writerow(list)

可能遇到的問題：直接使用這種寫法會(huì)導(dǎo)致文件每一行后面會(huì)多一個(gè)空行。

解決辦法如下：

out = open(outfile, "w", newline="")
csv_writer = csv.writer(out, dialect="excel")
csv_writer.writerow(list)

在stackoverflow上找到了比較經(jīng)典的解釋，原來 python3里面對(duì) str和bytes類型做了嚴(yán)格的區(qū)分，不像python2里面某些函數(shù)里可以混用。所以用python3來寫wirterow時(shí)，打開文件不要用wb模式，只需要使用w模式，然后帶上newline=''。

3、示例

簡單讀寫

import csv
 
class writer:
  def __init__(self):
    self.dict = {
      "標(biāo)題": "標(biāo)題",
      "鏈接": "鏈接",
      "服務(wù)": "服務(wù)",
      "dsr": "dsr",
      "店鋪名": "店鋪名",
      "價(jià)格": "店鋪名",
      "付款人數(shù)": "付款人數(shù)",
      "發(fā)貨地": "發(fā)貨地",
    }
    out = open("outfile.csv", "w", newline="")
    self.csv_writer = csv.writer(out, dialect="excel")
    self.csv_writer.writerow(self.dict)
 
  def writer_to(self, key_value):
    self.csv_writer.writerow(key_value)
 
 
if __name__ == "__main__":
  a = writer()
  new = {
    "鏈接": "http://www.baidu.com",
    "標(biāo)題": "我是標(biāo)題",
  }
  a.dict.update(new)
  print(a.dict)
  a.writer_to(a.dict.values())

結(jié)合爬蟲

import csv
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, NoSuchElementException
from selenium.webdriver.common.action_chains import ActionChains
 
driver = ["1", "2"]
colspan = ["1", "2"]
try:
  out = open("類目.csv", "w", newline="")
except PermissionError:
  print("文件被其他程序占用")
  input("")
csv_writer = csv.writer(out, dialect="excel")
csv_writer.writerow(["寶貝ID", "類目"])
 
 
def open_chrome():
  driver[0] = webdriver.Chrome()
  driver[0].get("https://www.dianchacha.com")
  input("請(qǐng)登陸后按回車:")
 
 
def EC_located(one_group, value):
  """
   目的：簡化代碼長度，參數(shù)1選擇one或者group切換選中模式
  :param value:要找的值【CSS選擇器】
  :return:選擇到的對(duì)象
  """
  wait = WebDriverWait(driver[0], 10)
  if one_group == "one":
    try:
      ecl = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, value)))
      return ecl
    except TimeoutException:
      print(value, "1元素未加載成功，等待超時(shí)")
  else:
    try:
      ecl = wait.until(
        EC.presence_of_all_elements_located((By.CSS_SELECTOR, value))
      )
      return ecl
    except TimeoutException:
      print(value, "1元素---組---未加載成功，等待超時(shí)")
 
 
def operating(ID):
  # 先獲取ID輸入框
  driver[0].get("https://www.dianchacha.com/item/info/index/iid/" + ID)
  html = driver[0].page_source
  if "未能找到親的寶貝" not in html:
    colspans = EC_located("group", ".colspan-1")
    colspan[0] = str(colspans[1].text).replace("寶貝類目： ", "")
  else:
    return operating(ID)
  print(colspan)
 
 
def writer_txt():
  csv_writer.writerow([url[0], colspan[0]])
  print("保存", url[0], colspan[0], "成功")
 
 
url = ["0", "1"]
 
 
def main():
  open_chrome()
  file = "寶貝ID.txt"
  with open(file) as f:
    for line in f.readlines():
      url[0] = line
      print(line)
      operating(url[0])
      writer_txt()
    out.close()
    print("已完成")
 
 
if __name__ == "__main__":
  main()

以上就是利用python 讀寫csv文件的詳細(xì)內(nèi)容，更多關(guān)于python 讀寫csv文件的資料請(qǐng)關(guān)注腳本之家其它相關(guān)文章！

您可能感興趣的文章: