# coding:utf-8
"""
總結(jié)一下，從網(wǎng)頁上抓取內(nèi)容大致分3步：
1、模擬瀏覽器訪問，獲取html源代碼
2、通過正則匹配，獲取指定標(biāo)簽中的內(nèi)容
3、將獲取到的內(nèi)容寫到文件中
"""
import requests # 用來抓取網(wǎng)頁的html源代碼
import csv # 將數(shù)據(jù)寫入到csv文件中
import random # 取隨機(jī)數(shù)
import time # 時(shí)間相關(guān)操作
import socket # 用于異常處理
import http.client # 用于異常處理
from bs4 import BeautifulSoup # 用來代替正則式取源碼中相應(yīng)標(biāo)簽中的內(nèi)容


# 獲取網(wǎng)頁中的html代碼
def get_content(url, data=None):
  header = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
  }
  timeout = random.choice(range(80, 180)) # timeout是設(shè)定的一個(gè)超時(shí)時(shí)間，取隨機(jī)數(shù)是因?yàn)榉乐贡痪W(wǎng)站認(rèn)定為網(wǎng)絡(luò)爬蟲
  while True:
    try:
      rep = requests.get(url, headers=header, timeout=timeout)
      rep.encoding = 'utf-8' # rep.encoding = ‘utf-8'是將源代碼的編碼格式改為utf-8
      break
    except socket.timeout as e:
      print('3:', e)
      time.sleep(random.choice(range(8, 15)))

    except socket.error as e:
      print('4:', e)
      time.sleep(random.choice(range(20, 60)))

    except http.client.BadStatusLine as e:
      print('5:', e)
      time.sleep(random.choice(range(30, 80)))

    except http.client.IncompleteRead as e:
      print('6:', e)
      time.sleep(random.choice(range(5, 15)))

  return rep.text


# 獲取html中我們所需要的字段
def get_data(html_text):
  final = []
  bs = BeautifulSoup(html_text, "html.parser") # 創(chuàng)建BeautifulSoup對(duì)象
  body = bs.body # 獲取body部分
  data = body.find('div', {'id': '7d'}) # 找到id為7d的div
  ul = data.find('ul') # 獲取ul部分
  li = ul.find_all('li') # 獲取所有的li

  for day in li: # 對(duì)每個(gè)li標(biāo)簽中的內(nèi)容進(jìn)行遍歷
    temp = []
    date = day.find('h1').string # 找到日期
    temp.append(date) # 添加到temp中
    inf = day.find_all('p') # 找到li中的所有p標(biāo)簽
    temp.append(inf[0].string, ) # 第一個(gè)p標(biāo)簽中的內(nèi)容（天氣狀況）加到temp中
    if inf[1].find('span') is None:
      temperature_highest = None # 天氣預(yù)報(bào)可能沒有當(dāng)天的最高氣溫（到了傍晚，就是這樣），需要加個(gè)判斷語句,來輸出最低氣溫
    else:
      temperature_highest = inf[1].find('span').string # 找到最高溫
      temperature_highest = temperature_highest.replace('℃', '') # 到了晚上網(wǎng)站會(huì)變，最高溫度后面也有個(gè)℃
    temperature_lowest = inf[1].find('i').string # 找到最低溫
    temperature_lowest = temperature_lowest.replace('℃', '') # 最低溫度后面有個(gè)℃，去掉這個(gè)符號(hào)
    temp.append(temperature_highest) # 將最高溫添加到temp中
    temp.append(temperature_lowest) # 將最低溫添加到temp中
    final.append(temp) # 將temp加到final中

  return final


# 寫入文件csv
def write_data(data, name):
  file_name = name
  with open(file_name, 'a', errors='ignore', newline='') as f:
    f_csv = csv.writer(f)
    f_csv.writerows(data)


if __name__ == '__main__':
  url = 'http://www.weather.com.cn/weather/101050101.shtml'
  html = get_content(url)
  result = get_data(html)
  write_data(result, 'weather.csv')