爬虫写入xls时报错

Tihool · 发表于 2022-4-17 20:54:40

马上注册，结交更多好友，享用更多功能^_^

您需要登录才可以下载或查看，没有账号？立即注册

x

import re
from bs4 import BeautifulSoup
import urllib.request
import xlwt
url = 'https://movie.douban.com/top250?start='
findlink = re.compile(r'<a href="(.*?)">')#电影链接
findimg = re.compile(r'<img .* src="(.*?)"/>',re.S)#图片链接
findname = re.compile(r'span class="title">(.*?)')#电影名
findpeople = re.compile(r'(\d*)人评价')#评价人数
findpoint = re.compile(r'(.*)')#评分
findother = re.compile(r'(.*?)',re.S) #获取导演等信息
findothers = re.compile(r'(.*?)') #获取其他信息
def main():
#解析网页源码
datas = Gteurl(url)
#保存数据
Savedata(datas)
def Gteurl(url):
for i in range(0,10):
 html = url + str(i*25)
 response = askURL(html)
 bs = BeautifulSoup(response,'html.parser')
 for item in bs.find_all('div',class_ = 'item'):
 data = []
 item = str(item)
 #1
 name = re.findall(findname, item)
 if len(name) == 2:
 cname = name[0]
 data.append(cname)
 oname = name[1].replace("\xa0/\xa0"," ")
 data.append(oname)
 else:
 data.append(name[0])
 data.append(' ')

 #2
 link = re.findall(findlink,item)[0]
 data.append(link)
 #7
 Img = re.findall(findimg,item)[0]
 Img = re.sub(r'width="100','',Img)
 Img = re.sub(r'"', '', Img)

 data.append(Img)
 #3
 nums = re.findall(findpeople,item)[0]
 data.append(nums)
 #6
 point = re.findall(findpoint,item)[0]

 data.append(point)
 #4
 other = re.findall(findother,item)[0]
 new_other = re.sub(' (\s+)?',' ',other)
 new_other = re.sub("\n",'',new_other)
 new_other = re.sub("\xa0", ' ', new_other)

 data.append(new_other)
 #5
 others = re.findall(findothers,item)
 if len(others) !=0:
 data.append(others[0])
 else:
 data.append(' ')

return data

def askURL(url): #封装数据，得到网页源码
head = {
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36 Edg/100.0.1185.39'
}
req =urllib.request.Request(url = url,headers=head,)#封装的信息，构建请求对象
response = urllib.request.urlopen(req)#发出请求
return response
def Savedata(data):
col = ('电影中文名','电影外国名','电影链接','图片链接','评价人数','评分','导演等信息','其他信息')
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('sheet1')
for a in range(8):
 worksheet.write(0,a,col[a])
for i in range(0,250):
 Data = data[i]
 for j in (0,8):
 worksheet.write(i+1,j,Data[j])#此处报错，string index out of range
worksheet.save('豆瓣250.xls')
if __name__ == '__main__':
main()
print('爬取完毕！')

isdkz · 发表于 2022-4-18 18:43:26

import re from bs4 import BeautifulSoup import urllib.request import xlwt url = 'https://movie.douban.com/top250?start=' findlink = re.compile(r'<a href="(.*?)">')#电影链接 findimg = re.compile(r'<img .* src="(.*?)"/>',re.S)#图片链接 findname = re.compile(r'span class="title">(.*?)')#电影名 findpeople = re.compile(r'(\d*)人评价')#评价人数 findpoint = re.compile(r'(.*)')#评分 findother = re.compile(r'(.*?)',re.S) #获取导演等信息 findothers = re.compile(r'(.*?)') #获取其他信息 def main(): #解析网页源码 datas = Gteurl(url) #保存数据 Savedata(datas) def Gteurl(url): datas = [] # 加了这行 for i in range(0,10): html = url + str(i*25) response = askURL(html) bs = BeautifulSoup(response,'html.parser') for item in bs.find_all('div',class_ = 'item'): data = [] item = str(item) #1 name = re.findall(findname, item) if len(name) == 2: cname = name[0] data.append(cname) oname = name[1].replace("\xa0/\xa0"," ") data.append(oname) else: data.append(name[0]) data.append(' ') #2 link = re.findall(findlink,item)[0] data.append(link) #7 Img = re.findall(findimg,item)[0] Img = re.sub(r'width="100','',Img) Img = re.sub(r'"', '', Img) data.append(Img) #3 nums = re.findall(findpeople,item)[0] data.append(nums) #6 point = re.findall(findpoint,item)[0] data.append(point) #4 other = re.findall(findother,item)[0] new_other = re.sub(' (\s+)?',' ',other) new_other = re.sub("\n",'',new_other) new_other = re.sub("\xa0", ' ', new_other) data.append(new_other) #5 others = re.findall(findothers,item) if len(others) !=0: data.append(others[0]) else: data.append(' ') datas.append(data) # 加了这行 return datas # 改了这行 def askURL(url): #封装数据，得到网页源码 head = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36 Edg/100.0.1185.39' } req =urllib.request.Request(url = url,headers=head,)#封装的信息，构建请求对象 response = urllib.request.urlopen(req)#发出请求 return response def Savedata(data): col = ('电影中文名','电影外国名','电影链接','图片链接','评价人数','评分','导演等信息','其他信息') workbook = xlwt.Workbook(encoding='utf-8') worksheet = workbook.add_sheet('sheet1') for a in range(8): worksheet.write(0,a,col[a]) for i, _ in enumerate(data): # 改了这行 Data = data[i] for j, v in enumerate(Data): # 改了这行 worksheet.write(i+1,j,v) # 改了这行 workbook.save('豆瓣250.xls') # 改了这行 if __name__ == '__main__': main() print('爬取完毕！')

账号		自动登录	找回密码
密码			立即注册