Edit "测试"

内容

### 3.基于代码的详细介绍

其实这一块我不想插入太多的代码段，因为我博客的markdown经常抽风，代码块可能会变的非常抽象。

```

from bs4 import BeautifulSoup
import re
import urllib.request, urllib.error
import xlwt

findLink = re.compile(r'<a href="(.*?)">') 
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)
findTitle = re.compile(r'(.*)')
findRating = re.compile(r'(.*)')
findJudge = re.compile(r'(\d*)人评价')
findInq = re.compile(r'(.*)')
findBd = re.compile(r'(.*?)', re.S)

def main():
    baseurl = "https://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = "test1.xls"
    saveData(datalist, savepath)

def getData(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)
 imgsrc = re.findall(findImgSrc, item)[0]
 data.append(imgsrc)
 titles = re.findall(findTitle, item)
 if len(titles) == 2:
 ctitle = titles[0]
 data.append(ctitle)
 otitle = titles[1].replace("/", "")
 data.append(otitle)
 else:
 data.append(titles[0])
 data.append(' ')
 rating = re.findall(findRating, item)[0]
 data.append(rating)
 judgenum = re.findall(findJudge, item)[0]
 data.append(judgenum)
 inq = re.findall(findInq, item)
 if len(inq) != 0:
 inq = inq[0].replace("。", "")
 data.append(inq)
 else:
 data.append(" ")
 bd = re.findall(findBd, item)[0]
 bd = re.sub(r'<br(\s+)?/>(\s+)?', "", bd)
 bd = re.sub('/', "", bd)
 data.append(bd.strip())
 datalist.append(data)
 return datalist

def askURL(url):
    head = {  
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122  Safari / 537.36"
    }
   
    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html

def saveData(datalist, savepath):
    print("save.......")
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  
    sheet = book.add_sheet('豆瓣电影Top250', cell_overwrite_ok=True)  
    col = ("电影详情链接", "图片链接", "影片中文名", "影片外国名", "评分", "评价数", "概况", "相关信息")
    for i in range(0, 8):
        sheet.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, 8):
            sheet.write(i + 1, j, data[j])  
    book.save(savepath)

if __name__ == "__main__":
    main()
    print("完成")

```