[英]KeyError while scraping with Python
我正在使用以下腳本從網站上抓取航班數據
import requests
import bs4
import csv
root_url = 'http://www.flightradar24.com/data/flights/3k601/'
response = requests.get(root_url)
soup = bs4.BeautifulSoup(response.text)
try:
table = soup.find('table')
rows = table.find_all('tr')
heads = [i.text.strip() for i in table.select('thead th')]
for tr in table.select('tbody tr'):
with open('flight_data.csv', 'a', newline='') as csvfile:
fieldnames = ['flight', 'From', 'To', 'Date', 'Aircraft', 'STD', 'ATD', 'STA', 'Status']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
flight_data = {}
flight_data['flight'] = tr['data-flight-number']
flight_data['From'] = " ".join(tr.select('td')[1].get_text().split())
flight_data['To'] = " ".join(tr.select('td')[2].get_text().split())
flight_data['Date'] = tr['data-date']
flight_data['Aircraft'] = " ".join(tr.select('td')[3].get_text().split())
flight_data['STD'] = tr.select('td')[4].get_text()
flight_data['ATD'] = tr.select('td')[5].get_text()
flight_data['STA'] = tr.select('td')[6].get_text()
flight_data['Status'] = " ".join(tr.select('td')[7].get_text().split())
print (flight_data)
writer.writerow(flight_data)
except AttributeError as e:
raise ValueError("No valid table found")
如果表中有數據,這將起作用,因為對於這樣的排期頁面,我試圖對鍵進行條件檢查
if tr['data-flight-number'] is None:
但是tr['data-flight-number']
不存在,因此在繼續抓取數據之前,如何測試該表是否為空?
使用get
if tr.get('somekey', None) is None
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.