外国语学院大二py实验报告4.1

```python
import urllib.request
import bs4
import urllib.parse
import glob

def accum(Dir,allFile):
    targetfile=glob.glob(pathname=Dir)
    print(targetfile)
    for file in targetfile:
        with open(file,'r',encoding='utf-8')as f:
            alltext=f.readlines()
            with open(allFile,'a',encoding='utf-8')as nf:
                nf.writelines(alltext)

url = "https://movie.douban.com/subject/35131346/reviews"
headers = {
    "user-agent":"Mozilla/5.0"
    }
request = urllib.request.Request(url,headers=headers)
response = urllib.request.urlopen(request)
soup = bs4.BeautifulSoup(response,'html.parser')
content = soup.find_all("div",class_="main-bd")

lists = []
num = 1
for i in content:
    item = i.find_all("div",class_="short-content")
    for c in item:
        lists.append(c.text)
        num = num+1
        if num==6:
            break

for i in range(5):
    with open("review"+str(i+1)+".txt",'w',encoding='utf-8') as q:
        q.writelines(lists[i])

accum(r'review*.txt',r'allreviews.txt')