使用Python selenium 爬取codis氣候資料服務系統資料並使用ggplot2繪製風花圖

LHB阿好伯, 2024/01/20

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select
service = Service("C:/Users/gtgrt/chromedriver_win32/chromedriver.exe")
driver = webdriver.Chrome(service=service)
driver.get("https://codis.cwa.gov.tw/StationData")
element = driver.find_element(By.XPATH, '//*[@id="auto_C0"]')
element.click()

# 定位下拉選單元素
select_element = driver.find_element(By.XPATH, '//*[@id="station_area"]')
# 創建Select對象
select = Select(select_element)
# 選擇下拉選單的一個選項，這裡以選擇第一個選項為例
select.select_by_index(15)  # 通過索引選擇

# 定位到 <input> 元素
input_element = driver.find_element(By.XPATH, '/html/body/div/main/div/div/div/div/aside/div/div[1]/div/div/section/ul/li[5]/div/div[2]/div/input')
# 向 <input> 元素輸入文本
input_element.send_keys("高雄 (467441)")


# 定位到按鈕元素
button_element = driver.find_element(By.XPATH, '/html/body/div[1]/main/div/div/section[1]/div[1]/div[3]/div[1]/div[1]/div[11]/div/div/div/div[2]')
# 點擊按鈕
button_element.click()
# 定位到按鈕元素
button_element = driver.find_element(By.XPATH, '/html/body/div[1]/main/div/div/section[1]/div[1]/div[3]/div[1]/div[1]/div[6]/div/div[1]/div/button')
# 點擊按鈕
button_element.click()

# 定位到按鈕元素
button_XPATH = "/html/body/div[1]/main/div/div/section[2]/div/div/section/div[5]/div[1]/div[2]/div"
button_element = driver.find_element(By.XPATH, button_XPATH)  # 使用變量而不是字符串

# 點擊按鈕
button_element.click()

button2_XPATH = '/html/body/div[1]/main/div/div/section[2]/div/div/section/div[5]/div[1]/div[1]/label/div/div[1]'
button2_element = driver.find_element(By.XPATH, button2_XPATH)  # 使用變量而不是字符串



import time

# 點擊按鈕
for i in range(0, 100):
    print(f"進行中：{i+1}/100")  # 顯示進度
    button2_element.click()
    try:
        button_element = WebDriverWait(driver, 5).until(
            EC.presence_of_element_located((By.XPATH, button_XPATH))
        )

    except:
        print("找不到指定的元素。")
    button_element.click()
    time.sleep(1)

for i in range(0, 100):
    print(f"進行中：{i+1}/100")  # 顯示進度
    button2_element.click()
    time.sleep(5)
    button_element.click()
    time.sleep(1)

#匯入C:\Users\gtgrt\OneDrive\00重要文件\成大碩士\06部落格\002_R語言\02_專案\中央氣象中的CSV

library(readr)
library(dplyr)
# 列出所有CSV檔案的路徑
file.list <- list.files(path="C:/Users/gtgrt/OneDrive/00重要文件/成大碩士/06部落格/002_R語言/02_專案/中央氣象", pattern="*.csv", full.names=TRUE)

# 定義一個函數來讀取每個檔案並添加編號和日期欄位
read_and_add_info <- function(file_path) {
  # 從檔案路徑提取編號和日期
  file_name <- basename(file_path)
  parts <- strsplit(file_name, "-|\\.")[[1]]
  code <- parts[1]
  date <- paste(parts[2], parts[3], parts[4], sep="-")
  
  # 讀取CSV檔案
  data <- read.csv(file_path, stringsAsFactors = FALSE)
  
  # 添加編號和日期欄位
  data$code <- code
  data$date <- date
  
  return(data)
}

# 讀取所有檔案並合併
combined_data <- lapply(file.list, read_and_add_info) %>% bind_rows()

# 檢視合併後的數據框
head(combined_data)
str(combined_data)

library(dplyr)
library(ggplot2)

# 確保氣溫是數值型別
combined_data$氣溫... <- as.numeric(combined_data$氣溫...)

# 將日期轉換為日期型別（如果尚未轉換）
combined_data$date <- as.Date(combined_data$date, format="%Y-%m-%d")

# 從日期中提取月份
combined_data$month <- format(combined_data$date, "%Y-%m")

# 繪製箱型圖
ggplot(combined_data, aes(x=month, y=氣溫..., group=month)) +
  geom_boxplot() +
  labs(title="每月氣溫箱型圖", x="月份", y="氣溫 (°C)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) # 調整x軸標籤角度以便閱讀

# 計算每日的平均氣溫、最大氣溫和最小氣溫
library(dplyr)
library(ggplot2)

# 確保氣溫是數值型別
combined_data$氣溫... <- as.numeric(combined_data$氣溫...)

# 計算每日的平均氣溫、最大氣溫和最小氣溫
daily_temp <- combined_data %>%
  group_by(date) %>%
  summarise(
    AvgTemp = mean(氣溫..., na.rm = TRUE),
    MaxTemp = max(氣溫..., na.rm = TRUE),
    MinTemp = min(氣溫..., na.rm = TRUE)
  )

# 移除包含NA值的行
daily_temp <- daily_temp %>%
  filter(!is.na(AvgTemp) & !is.na(MaxTemp) & !is.na(MinTemp))

# 繪製圖表
ggplot(daily_temp, aes(x=date)) +
  geom_line(aes(y=AvgTemp), color="blue") +
  geom_ribbon(aes(ymin=MinTemp, ymax=MaxTemp), alpha=0.2) +
  labs(title="每日氣溫平均值與最大/最小值區間", x="日期", y="氣溫 (°C)") +
  theme_minimal()


# 安裝和加載openair包
if (!require(openair)) {
  install.packages("openair")
  library(openair)
}

# 確保風速和風向是正確的數值型別
combined_data$風速.m.s. <- as.numeric(combined_data$風速.m.s.)
combined_data$風向.360degree. <- as.numeric(combined_data$風向.360degree.)

# 繪製風花圖
windRose(combined_data, ws = "風速.m.s.", wd = "風向.360degree.")
data3 <- combined_data
data3$windDirection_N <- cut(as.numeric(combined_data$風向.360degree.),
                             breaks = c(0, 11.26, 33.76, 56.26, 78.76, 101.26, 127.76, 146.26, 168.76, 191.26, 213.76, 236.26, 258.76, 281.26, 303.76, 326.26, 348.75, 360),
                             labels = c("N","NNE","NE","ENE","E","ESE","ES","SSE","S","SWS","SW","WSW","W","WNW","NW","NNW","N"),
                             #   labels = c("北","北東北","東北","東東北","東","東東南","東南","南東南","南","南西南","西南","西西南","西","西西北","西北","西北西","北"),
                             include.lowest = TRUE)
data3$Windspeed_N <- cut(as.numeric(combined_data$風速.m.s.),
                         breaks =c(0, 2.1, 4.1,  6.1, Inf),
                         labels = c("0~2", "2.1~4", "4.1~6", ">6.1"),
                         right = F)
data3$Windspeed <- as.numeric(data3$Windspeed)
ggplot(data = data3, aes(x = windDirection_N, fill = Windspeed_N))+
  geom_bar( position = position_stack(reverse = TRUE)) + 
  theme_bw() +
  scale_fill_discrete(guide = guide_legend(reverse=TRUE), name = "Wind Speed (m/s)")+
  coord_polar(start = -0.3) + 
  xlab("") 


windD <- (c("N","NNE","NE","ENE","E","ESE","SE","SSE","S","SSW","SW","WSW","W","WNW","NW","NNW","N"))
FourSeasons2 <- factor(c("冬","春","夏","秋","冬"))
lab_max <- 30
plottitle <- "風向與風速分佈圖"
ggplot(data = data3, aes(x = windDirection_N, fill = Windspeed_N))+
  geom_bar(aes(y = (..count..)/sum(..count..)*100 ), 
           position = position_stack(reverse = TRUE)) +
  theme_bw() + scale_x_discrete(drop = FALSE,
                                limits= windD) +
  scale_fill_discrete(guide = guide_legend(reverse=TRUE), name = "Wind Speed (m/s)")+
  coord_polar(start = -0.2) + 
  annotate("text",x = "NE", 
           y = c(scales::extended_breaks(5)(range(0,as.numeric(lab_max)))), 
           label = paste(c(scales::extended_breaks(5)(range(0,as.numeric(lab_max)))),"%"))+
  xlab("") + ggtitle(plottitle) + ylab("%") +
  theme(legend.text=element_text(family = "Times New Roman"))+
  theme(legend.title=element_text(family = "Times New Roman"))+
  theme(axis.title.y = element_text(family = "Times New Roman"))+
  theme(title=element_text(family = "DFKai-SB"))+
  theme(axis.title=element_blank(), 
        axis.text.y=element_blank(), 
        axis.ticks=element_blank())