对于新手做Python爬虫来说是有点难处的，前期练习的时候可以直接套用模板，这样省时省力还很方便。
使用Python爬取某网站的相关数据，并保存到同目录下Excel。
直接上代码：
import re
import urllib
.error
import urllib
.request
import xlwt
from bs4
import BeautifulSoup
def main():
baseurl
="http://jshk.com.cn"
datelist
= getDate
(baseurl
)
savepath
=".\\jshk.xls"
saveDate
(datelist
,savepath
)
# askURL("http://jshk.com.cn/")
findlink
= re
.compile(r'')
findimg
= re
.compile(r',re.S)
findtitle = re.compile(r'(.*))
findrating = re.compile(r'(.*))
findjudge = re.compile(r'(\d*)人评价')
findinq= re.compile(r'(.*)')
def getDate(baseurl):
datalist =[]
for i in range(0,10):
url=baseurl+str(i*25)
html=askURL(url)
soup = BeautifulSoup(html,"html.parser")
for item in soup.find_all('div',class_="item"):
data = []
item = str(item)
link = re.findall(findlink,item)[0]
data.append(link)
img=re.findall(findimg,item)[0]
data.append(img)
title=re.findall(findtitle,item)[0]
rating=re.findall(findrating,item)[0]
data.append(rating)
judge=re.findall(findjudge,item)[0]
data.append(judge)
inq=re.findall(findinq,item)
if len(inq)!=0:
inq=inq[0].replace("。","")
data.append(inq)
else:
data.append(" ")
print(data)
datalist.append(data)
print(datalist)
return datalist
def askURL(url):
head = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36"}
request=urllib.request.Request(url,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
def saveDate(datalist,savepath):
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('电影',cell_overwrite_ok=True)
col =("电影详情","图片","影片","评分","评价数","概况")
for i in range(0,5):
worksheet.write(0,i,col[i])
for i in range(0,250):
print("第%d条" %(i+1))
data=datalist[i]
for j in range(0,5):
worksheet.write(i+1,j,data[j])
workbook.save(savepath)
if __name__ == '__main__':
main()
print("爬取完毕")
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
直接复制粘贴就行。
若要更改爬取网站，则需要更改URL以及相应的html格式（代码中的“item”）。
