python爬虫——爬取数据导入excel表

谁践踏了优雅 2023-03-01 12:37 62阅读 0赞

### 1、导入第三方库 ###

requests库、re、html、xlwt

from bs4 import BeautifulSoup #解析网页
    import re #正则表达式，进行文字匹配
    import urllib.request,urllib.error  #制定url，获取网页数据
    import xlwt  #进行excel操作
    import sqlite3  #进行SQLite数据库操作

### 2、申请访问网页 ###

def askURL(url):
        head = {
        
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.116 Safari/537.36"
        } #伪装成网页的形式，请求网页信息
        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

url：想要爬取的网址

User-Agent获取方法：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dldHNfcw_size_16_color_FFFFFF_t_70]

### 3、获取数据（正则表达式） ###

#电影链接
 findLink = re.compile(r'<a href="(.*?)">')
 #封面图片
 findImgSrc = re.compile(r'<img.*src="(.*?)".*>',re.S)
 #电影名称
 findTitle = re.compile(r'(.*)')
 #评分
 findRating = re.compile(r'(.*)')
 #评价人数
 findJudge = re.compile(r'(\d*)人评价')
 #概况
 findInq = re.compile(r'(.*)')
 #电影详细内容
 findBd = re.compile(r'(.*?)',re.S)

通过查看网页源代码，找出要获取数据的“格式”，用正则表达式来获取数据  
（.\*?）是要获取的数据，不加括号则无法获取

### 4、创建excel表 ###

book = xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet = book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
    book.save('豆瓣电影Top250.xls')

创建完成后，将数据导入到excel表中

--------------------

**【完整代码】**

from bs4 import BeautifulSoup #解析网页
 import re #正则表达式，进行文字匹配
 import urllib.request,urllib.error #制定url，获取网页数据
 import xlwt #进行excel操作
 import sqlite3 #进行SQLite数据库操作
 
 def main():
 baseurl = "https://movie.douban.com/top250?start="
 #爬取网页
 datalist = getData(baseurl)
 #保存数据
 savepath = "豆瓣电影Top250.xls"
 saveData(datalist,savepath)
 #电影链接
 findLink = re.compile(r'<a href="(.*?)">')
 #封面图片
 findImgSrc = re.compile(r'<img.*src="(.*?)".*>',re.S)
 #电影名称
 findTitle = re.compile(r'(.*)')
 #评分
 findRating = re.compile(r'(.*)')
 #评价人数
 findJudge = re.compile(r'(\d*)人评价')
 #概况
 findInq = re.compile(r'(.*)')
 #电影详细内容
 findBd = re.compile(r'(.*?)',re.S)
 
 #爬取网页
 def getData(baseurl):
 datalist = []
 for i in range(0,10):
 url = baseurl + str(i*25)
 html = askURL(url)
 
 
 #逐一解析数据
 soup = BeautifulSoup(html,"html.parser")
 for item in soup.find_all('div',class_="item"):
 #print(item)
 data = []
 item = str(item)
 
 Link = re.findall(findLink,item)[0]
 data.append(Link)
 
 ImgSrc = re.findall(findImgSrc,item)[0]
 data.append(ImgSrc)
 
 Title = re.findall(findTitle,item)
 if len(Title)==2:
 ctitle = Title[0]
 data.append(ctitle)
 otitle = Title[1].replace("/","")
 data.append(otitle)
 else:
 data.append(Title[0])
 data.append(' ')
 
 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(" ")
 
 Bd = re.findall(findBd,item)[0]
 Bd = re.sub('<br(\s+)?/>(\s+)?'," ",Bd)
 data.append(Bd.strip())
 
 datalist.append(data) #把处理好的一个电影信息存储到datalist中
 #解析网页
 return datalist
 
 #获取指定一个网页内容
 def askURL(url):
 head = {
 
 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.116 Safari/537.36"
 } #伪装成网页的形式，请求网页信息
 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
 #保存数据
 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","封面链接","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('豆瓣电影Top250.xls')
 
 
 main()
 print("爬取完毕")

**【运行结果】**

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dldHNfcw_size_16_color_FFFFFF_t_70_pic_center]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dldHNfcw_size_16_color_FFFFFF_t_70_pic_center 1]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dldHNfcw_size_16_color_FFFFFF_t_70]: /images/20230208/a89ce933c00f416ea50171d4d83a3493.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dldHNfcw_size_16_color_FFFFFF_t_70_pic_center]: /images/20230208/80eef08110bc4141850c1740577a00b8.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dldHNfcw_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20230208/e551ba22a1ff421391f9eef4763fc952.png