python爬虫豆瓣新人求助
from bs4 import BeautifulSoup #网页解析，获取数据import urllib.request,urllib.error #制定URL，获取网页数据
def main():
baseurl = "https://movie.douban.com/top250?start="
#1.爬取网页
datalist = getData(baseurl)
savepath = "豆瓣电影Top250.xls"
#3.保存数据
saveData(savepath)
askUPL("https://movie.douban.com/top250?start=")
#爬取网页
def getData(baseurl):
datalist = []
for i in range(0,10):
url = baseurl+str(i*25)
html = askUPL(url)
#2.逐一解析数据
return datalist
#得到指定一个URL的网页内容
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
# 保存数据
def saveData(savepath):
print("save....")
if __name__ == "__main__":
main()
为什么一直运行不出来啊？一直显示这个{:10_266:} {:10_266:}
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
ameError: name 'askUPL' is not defined
为什么askUPL未声明呢？
是不是顺序的问题？ 本帖最后由 YunGuo 于 2021-2-19 00:36 编辑
html = askUPL(url)
这里错了一个字母，也就是报错的第24行代码，你定义的函数名是askURL，打成了askUPL
页:
[1]