list1=[]
list2=[]
list3=[]
list4=[]
import requests
from bs4 import BeautifulSoup
req=requests.get('https://www.360kan.com/dianshi/list.php?cat=113')
req.encoding=req.apparent_encoding
soup=BeautifulSoup(req.text,'lxml')
page=1
print('当前是:%s***********'%page)
for t in soup.find_all('a','js-tongjic'):
print(t.text,'https://www.360kan.com'+t['href'])
for t in soup.find_all('span','s1'):
list1.append(t.text)
for t in soup.find_all('p','star'):
list2.append(t.text)
for t in soup.find_all('span','hint'):
list3.append(t.text)
for t in soup.find_all('a','js-tongjic'):
list4.append('https://www.360kan.com'+t['href'])
for test in soup.find('div','ew-page').find_all('a')[1:8]:
print(test['href'])
page=page+1
print('当前是:%s***********'%page)
req2=requests.get(test['href'])
req2.encoding=req2.apparent_encoding
soup2=BeautifulSoup(req2.text,'lxml')
for t in soup2.find_all('span','s1'):
list1.append(t.text)
for t in soup2.find_all('p','star'):
list2.append(t.text)
for t in soup2.find_all('span','hint'):
list3.append(t.text)
for t in soup2.find_all('a','js-tongjic'):
list4.append('https://www.360kan.com'+t['href'])
for t in soup2.find_all('a','js-tongjic'):
print(t.text,'https://www.360kan.com'+t['href'])
import xlwt
n=len(list1)
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('teleplay')
worksheet.write(0, 0, label='电视剧名')
worksheet.write(0,2, label='主演')
worksheet.write(0,10, label='总集数')
worksheet.write(0,14, label='链接')
for i in range (1,n+1):
worksheet.write(i,0,label=list1[i-1])
worksheet.write(i,2,label=list2[i-1])
worksheet.write(i,10,label=list3[i-1])
worksheet.write(i,12,label=list4[i-1])
workbook.save('Excel_telepaly.xls')
list2=[]
list3=[]
list4=[]
import requests
from bs4 import BeautifulSoup
req=requests.get('https://www.360kan.com/dianshi/list.php?cat=113')
req.encoding=req.apparent_encoding
soup=BeautifulSoup(req.text,'lxml')
page=1
print('当前是:%s***********'%page)
for t in soup.find_all('a','js-tongjic'):
print(t.text,'https://www.360kan.com'+t['href'])
for t in soup.find_all('span','s1'):
list1.append(t.text)
for t in soup.find_all('p','star'):
list2.append(t.text)
for t in soup.find_all('span','hint'):
list3.append(t.text)
for t in soup.find_all('a','js-tongjic'):
list4.append('https://www.360kan.com'+t['href'])
for test in soup.find('div','ew-page').find_all('a')[1:8]:
print(test['href'])
page=page+1
print('当前是:%s***********'%page)
req2=requests.get(test['href'])
req2.encoding=req2.apparent_encoding
soup2=BeautifulSoup(req2.text,'lxml')
for t in soup2.find_all('span','s1'):
list1.append(t.text)
for t in soup2.find_all('p','star'):
list2.append(t.text)
for t in soup2.find_all('span','hint'):
list3.append(t.text)
for t in soup2.find_all('a','js-tongjic'):
list4.append('https://www.360kan.com'+t['href'])
for t in soup2.find_all('a','js-tongjic'):
print(t.text,'https://www.360kan.com'+t['href'])
import xlwt
n=len(list1)
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('teleplay')
worksheet.write(0, 0, label='电视剧名')
worksheet.write(0,2, label='主演')
worksheet.write(0,10, label='总集数')
worksheet.write(0,14, label='链接')
for i in range (1,n+1):
worksheet.write(i,0,label=list1[i-1])
worksheet.write(i,2,label=list2[i-1])
worksheet.write(i,10,label=list3[i-1])
worksheet.write(i,12,label=list4[i-1])
workbook.save('Excel_telepaly.xls')