贪睡的苏简 发表于 2021-4-6 23:18:36

怎么把豆瓣爬到的数据放进去一个表格里啊

import requests
import bs4
import openpyxl
import os
os.chdir("D:\BianCheng\Pythonwork\爬虫爬出来资料")

header ={}
header['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'

def open_url(url):
    res = requests.get(url, headers=header)
    return res

def look_movie(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    targets = soup.find_all("div", class_='hd')
    list1 = []
    for each in targets:
      list1.append(each.a.span.text)
    return list1

def main():
    yeshu = 0

    while yeshu <= 25:
      url = "http://movie.douban.com/top250?start=" + str(yeshu) + "&filter="
      res = open_url(url)
      data = look_movie(res)
      yeshu += 25
      print(data)
    # to_excel(data)这个就是存表格的，但运行它就报错，不运行注释了就正常...

def to_excel(data):
    wb = openpyxl.Workbook()
    wb.guess_types = True
    ws = wb.active
    ws.append(['1','2','3','4','5'])
    for each in data:
      ws.append(each)

    wb.save("豆瓣250电影榜.xlsx")

if __name__ == '__main__':
    main()


我根据极客爬虫篇里摘取出一些可以用的，但就是用不了现在，希望有小伙伴解救一下谢谢

591821661 发表于 2021-4-7 00:00:32

终于帮你改完了 满意请给最佳


import requests
import bs4
import openpyxl

import os
# os.chdir("D:\BianCheng\Pythonwork\爬虫爬出来资料")

header ={'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'}

def open_url(url):
    res = requests.get(url, headers=header)
    return res


def look_movie(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    targets = soup.find_all("div", class_='hd')
    list1 = []
    for each in targets:
      list1.append(each.a.span.text)
    return list1


def main():
    yeshu = 0

    data = []
    while yeshu <= 225:
      url = "http://movie.douban.com/top250?start=" + str(yeshu) + "&filter="
      res = open_url(url)
      data.extend(look_movie(res))
      yeshu += 25
    to_excel(data, yeshu)


def to_excel(data, yeshu):
    wb = openpyxl.Workbook()
    wb.guess_types = True
    ws = wb.active
    data_rank =
    ws.append(data_rank)
    for movie_rank,movie_name in zip(data_rank, data):
      print("%s 排名:%s" % (movie_name, movie_rank))
    print(data)
    ws.append(data)
    wb.save("豆瓣250电影榜.xlsx")


if __name__ == '__main__':
    main()

贪睡的苏简 发表于 2021-4-7 01:08:54

591821661 发表于 2021-4-7 00:00
终于帮你改完了 满意请给最佳

多谢大佬解惑

贪睡的苏简 发表于 2021-4-7 10:10:36

根据大佬的代码，自己弄出了自己想要的部分模样{:10_298:}
import requests
import bs4
import openpyxl

#import os
# os.chdir("D:\BianCheng\Pythonwork\爬虫爬出来资料")

header ={'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'}

def open_url(url):
    res = requests.get(url, headers=header)
    return res


def look_movie(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    targets = soup.find_all("div", class_='hd')
    data = []
    for each in targets:
      data.append(each.a.span.text)
    return data


def main():
    yeshu = 0

    data = []
    while yeshu <= 225:
      url = "http://movie.douban.com/top250?start=" + str(yeshu) + "&filter="
      res = open_url(url)
      data.extend(look_movie(res))
      yeshu += 25
    to_excel(data, yeshu)


def to_excel(data, yeshu):
    wb = openpyxl.Workbook()
    wb.guess_types = True
    ws = wb.active
    #表格三件套

    # data_rank =

    # for movie_rank,movie_name in zip(data_rank, data):
    #   print("%s 排名:%s" % (movie_name, movie_rank))
    nub = 0
    data_rank = []
    kongge = []
    for i in range(1,251):
      data_rank.append("第%d名"%i)
      if i % 10 == 0:
            ws.append(data_rank)
            ws.append(data)
            ws.append(kongge)
            nub += 10
            data_rank = []

    wb.save("豆瓣250电影榜.xlsx")


if __name__ == '__main__':
    main()
页: [1]
查看完整版本: 怎么把豆瓣爬到的数据放进去一个表格里啊