python-爬虫-css提取-写入csv-爬取猫眼电影榜单
猫眼有一个电影榜单top100，我们将他的榜单电影数据（电影名、主演、上映时间、豆瓣评分）抓下来保存到本地的excle中
本案例使用css方式提取页面数据，所以会用到以下库
importtimeimportrequestsimportparsel#解析库，解析css importcsv#爬取的数据写入csv
创建csv文件标头信息，也就是表格第一排内容
f = open('book.csv',mode='a',encoding='utf-8',newline='')#表头 csv_writer = csv.DictWriter(f,fieldnames=['电影名字','主演','上映时间','评分'])
csv_writer.writeheader()
分析地址，每一页地址的区别在最后一个“=”号后面的数字，第一页是“10“，第二页是”20“，以此类推到”90“，所以写个循环翻页
https://www.maoyan.com/board/4?timeStamp=1680685769327&channelId=40011&index=8&signKey=6fa9e474efd1ed595c394e9bc497cdaf&sVersion=1&webdriver=false&offset=10
https://www.maoyan.com/board/4?timeStamp=1680685769327&channelId=40011&index=8&signKey=6fa9e474efd1ed595c394e9bc497cdaf&sVersion=1&webdriver=false&offset=20
https://www.maoyan.com/board/4?timeStamp=1680685769327&channelId=40011&index=8&signKey=6fa9e474efd1ed595c394e9bc497cdaf&sVersion=1&webdriver=false&offset=90
for page in range(0,10):
time.sleep(2)
page= page *10url= 'https://www.maoyan.com/board/4?timeStamp=1680685769327&channelId=40011&index=8&signKey=6fa9e474efd1ed595c394e9bc497cdaf&sVersion=1&webdriver=false&offset={}'.format(page)print(url)
分析页面，找到需要的数据
提取数据脚本如下
response = requests.get(url, headers=headers)
selector=parsel.Selector(response.text)
li_s= selector.css('.board-wrapper dd')for li inli_s:
name= li.css('.name a::text').get()#电影名称 star = li.css('.star::text').get()#主演 star_string =star.strip()#strip() 方法用于移除字符串头尾指定的字符(默认为空格或换行符)或字符序列 releasetime = li.css('.releasetime::text').get()#上映时间 data_time =releasetime.strip()
follow= li.css('.score i::text').getall()
score= ''.join(follow)#join函数将列表内的值连串显示，参考“https://blog.csdn.net/weixin_50853979/article/details/125119368”
最后将获取到的数据字典化后存到csv文件中
dit ={'电影名字': name,'主演': star_string,'上映时间': data_time,'评分': score,
}
csv_writer.writerow(dit)
执行后csv文件的内容
全部代码
importtimeimportrequestsimportparsel#解析库，解析css importcsv#爬取的数据写入csv f= open('book.csv',mode='a',encoding='utf-8',newline='')#表头 csv_writer = csv.DictWriter(f,fieldnames=['电影名字','主演','上映时间','评分'])
csv_writer.writeheader()for page in range(0,10):
time.sleep(2)
page= page *10url= 'https://www.maoyan.com/board/4?timeStamp=1680685769327&channelId=40011&index=8&signKey=6fa9e474efd1ed595c394e9bc497cdaf&sVersion=1&webdriver=false&offset={}'.format(page)print(url)
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36','Cookie': '__mta=20345351.1670903159717.1670903413872.1670903436333.5; uuid_n_v=v1; uuid=A8065B807A9811ED82C293D7E110319C9B09821067E1411AB6F4EC82889E1869; _csrf=916b8446658bd722f56f2c092eaae35ea3cd3689ef950542e202b39ddfe7c91e; Hm_lvt_703e94591e87be68cc8da0da7cbd0be2=1670903160; _lxsdk_cuid=1850996db5dc8-07670e36da28-26021151-1fa400-1850996db5d67; _lxsdk=A8065B807A9811ED82C293D7E110319C9B09821067E1411AB6F4EC82889E1869; __mta=213622443.1670903327420.1670903417327.1670903424017.4; Hm_lpvt_703e94591e87be68cc8da0da7cbd0be2=1670903436; _lxsdk_s=1850996db5e-8b2-284-88a%7C%7C18','Host': 'www.maoyan.com','Referer': 'https://www.maoyan.com/films/1200486'}
response= requests.get(url, headers=headers)
selector=parsel.Selector(response.text)
li_s= selector.css('.board-wrapper dd')for li inli_s:
name= li.css('.name a::text').get()#电影名称 star = li.css('.star::text').get()#主演 star_string =star.strip()#strip() 方法用于移除字符串头尾指定的字符(默认为空格或换行符)或字符序列 releasetime = li.css('.releasetime::text').get()#上映时间 data_time =releasetime.strip()
follow= li.css('.score i::text').getall()
score= ''.join(follow)#join函数将列表内的值连串显示，参考“https://blog.csdn.net/weixin_50853979/article/details/125119368” dit ={'电影名字': name,'主演': star_string,'上映时间': data_time,'评分': score,
}
csv_writer.writerow(dit)