from bs4 import BeautifulSoup #網頁決議，獲取資料
import urllib.request,urllib.error #制定URL，獲取網頁資料
def main():
baseurl = "https://movie.douban.com/top250?start="
#1.爬取網頁
datalist = getData(baseurl)
savepath = "豆瓣電影Top250.xls"
#3.保存資料
saveData(savepath)
askUPL("https://movie.douban.com/top250?start=")
#爬取網頁
def getData(baseurl):
datalist = []
for i in range(0,10):
url = baseurl+str(i*25)
html = askUPL(url)
#2.逐一決議資料
return datalist
#得到指定一個URL的網頁內容
def askURL(url):
head = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36 Edg/88.0.705.68"
}
request = urllib.request.Request(headers = head)
html = ""
try:
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
print(html)
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
return html
# 保存資料
def saveData(savepath):
print("save....")
if __name__ == "__main__":
main()
為什么一直運行不出來啊？一直顯示這個
D:\douban\venv\Scripts\python.exe D:/douban/venv/spider.py
Traceback (most recent call last):
File "D:/douban/venv/spider.py", line 51, in <module>
main()
File "D:/douban/venv/spider.py", line 13, in main
datalist = getData(baseurl)
File "D:/douban/venv/spider.py", line 24, in getData
html = askUPL(url)
NameError: name 'askUPL' is not defined
uj5u.com熱心網友回復：
網址沒有輸錯，復制過來換行了轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/260766.html