#3601
#coded by 伊瑪目的門徒
import re
import requests
import time
from bs4 import BeautifulSoup
import pandas as pd
urllist=[]
titlelist=[]
list0=[]
start = time.clock() # 計時-開始
from concurrent.futures import ThreadPoolExecutor
header={'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.XXXX.XXX Safari/537.36'}
def do(i):
try:
cd=[]
html=requests.get('http://www.zcfudao.com/article/qyjs/p'+str(i)+'.html',headers=header)
html.encoding='utf-8'
#print (html.text)
Soup = BeautifulSoup(html.text, "lxml")
#ab=Soup.select('li a[target="_blank"]')
ab=Soup.select('tr')[1:]
#print (ab)
for x in ab:
#print (x)
list0.append(x)
print (i)
list1.remove(i)
except:
pass
# 多線程
def multithreading():
sum=0
while len(list1)>0:
with ThreadPoolExecutor(max_workers=10) as executor:
for result in executor.map(do, list1):
sum+=1
return sum
list1=list(range(1,3602,1))
sum=multithreading()
print ('還剩下{}頁'.format(list1))
end = time.clock() # 計時-結束
print (("爬取完成 用時:"))
print ((end - start))
print ('總爬取 %d 頁 '%(sum))
num=[]
nam=[]
pname=[]
year_t=[]
money=[]
type0=[]
for thing in list0:
thing=list(thing)
#print (thing)
if len(thing)==0:
pass
else:
num.append(thing[1])
nam.append(thing[3])
pname.append(thing[5])
year_t.append(thing[7])
money.append(thing[9])
type0.append(thing[11])
df=pd.DataFrame({'num':num,
'nam':nam,
'pname':pname,
'year_t':year_t,
'money':money,
'type0':type0})
print (df)
df.to_excel('2.xlsx', index=False)
'''
#可作爲TXT輸出
with open("test.txt","w") as f:
for thing in list0:
f.write(str(thing))
f.write('\r\n')
'''