前言
因为有些无聊，所以想看看有没有好看的电影，搜着搜着就看到了豆瓣电影TOP250的榜单，手痒就想把它给爬下来存到Execl（毕竟熟能生巧，要勤加练习嘛，胡说，明明是看着人家好爬！），然后做了一定的数据清洗和分析，绘制了几张图表，不得不说，图一出来，一些数据就更加一目了然了。代码比较简单，写得比较糙，可以给新手学习学习，大神请飘过（欢迎指正），话不多说，先上代码！
代码
import re
import requests
import wordcloud
import matplotlib.pyplot as plt
from bs4 import BeautifulSoup
from openpyxl import Workbook
from openpyxl.styles import Alignment
def top250():
wb = Workbook()
ws = wb.get_sheet_by_name('Sheet')
num = 0
num1 = 0
lst = []
name_lst = []
dy_lst = []
zy_lst = []
time_lst = []
a = []
country_lst = []
country_lst1 = []
leixing_lst = []
pj_lst = []
people_lst = []
quote_lst = []
time_dict = {}
country_dict = {}
headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36 Edg/81.0.416.68",
}
while num <= 225:
url = 'https://movie.douban.com/top250?start=' + str(num) + '&filter='
with requests.get(url=url, headers=headers) as r:
if r.status_code == 200:
r.encoding = r.apparent_encoding
soup = BeautifulSoup(r.text, 'html.parser')
ol = soup.find('ol')
li = ol.find_all('li')
for i in li:
name = i.find('span').text
p = i.find('p')
p = str(p).split('<br/>', 1)
fst = p[0].split('>', 1)[1]
sec = p[1].split('<', 1)[0]
daoyan = fst.split('主', 1)[0]
daoyan = daoyan.replace('导演:', '')
daoyan = daoyan.replace('\xa0', '')
daoyan = daoyan.replace('\n ', '')
try:
zhuyan = fst.split('主演:', 1)[1]
except:
zhuyan = ''
time = sec.split(' / ', 2)[0]
time = time.replace('\xa0', '')
time = time.replace('\n ', '')
time = re.findall(r'\d{4}', time)[-1]
country = sec.split(' / ', 2)[1]
country = country.replace('\xa0', '')
type = sec.split(' / ', 2)[2]
type = type.replace('\xa0', '')
type = type.replace('\n ', '')
star = i.find('div', attrs={'class': "star"})
span = star.find_all('span')
pingjia = span[1].text
people = span[3].text.split('评价', 1)[0]
try:
quote = i.find('p', attrs={'class': "quote"}).text
quote = quote.replace('\n', '')
except:
quote = ''
name_lst.append(name)
dy_lst.append(daoyan)
zy_lst.append(zhuyan)
time_lst.append(time)
country_lst.append(country)
leixing_lst.append(type)
pj_lst.append(pingjia)
people_lst.append(people)
quote_lst.append(quote)
if num1 == 9:
time_lst1 = list(map(int, time_lst))
for i in range(len(country_lst)):
a.append(country_lst[i].split(' '))
for j in range(len(a[i])):
country_lst1.append(a[i][j])
for i in set(time_lst1):
time_dict[i] = time_lst1.count(i)
for i in set(country_lst1):
country_dict[i] = country_lst1.count(i)
plt.rcParams['font.sans-serif'] = ['SimHei']
fig1 = plt.figure()
fig2 = plt.figure().add_subplot(111)
ax1 = fig1.add_subplot(3, 1, 1)
ax2 = fig1.add_subplot(3, 1, 2)
ax3 = fig1.add_subplot(3, 1, 3)
for key in time_dict:
ax1.text(key, time_dict[key], '%s' % time_dict[key], ha='center', va='bottom')
ax2.text(key, time_dict[key], '%s' % time_dict[key], ha='center', va='bottom')
for key in country_dict:
ax3.text(key, country_dict[key], '%s' % country_dict[key], ha='center', va='bottom')
ax1.bar(time_dict.keys(), time_dict.values(), color='indianred', alpha=0.8)
ax2.plot(list(time_dict.keys()), list(time_dict.values()), color='indianred', alpha=0.8)
ax3.bar(country_dict.keys(), country_dict.values(), color='indianred', alpha=0.8)
ax1.set_title("豆瓣电影TOP250各年份上榜电影次数柱形图分析")
# 为两条坐标轴设置名称
ax1.set_xlabel("年份")
ax1.set_ylabel("次数")
ax2.set_title("豆瓣电影TOP250各年份上榜电影次数折线图分析")
# 为两条坐标轴设置名称
ax2.set_xlabel("年份")
ax2.set_ylabel("次数")
ax3.set_title("豆瓣电影TOP250各地区上榜电影次数柱形图分析")
# 为两条坐标轴设置名称
ax3.set_xlabel("地区")
ax3.set_ylabel("次数")
ax3.set_xticklabels(country_dict.keys(), fontsize=10, rotation=30)
fig1.set_figwidth(15)
# 读取image
background_img = plt.imread('heart.jpg')
# 生成wordcloud 对象
wc = wordcloud.WordCloud(background_color='white', mask=background_img, scale=2, font_path='C:/Windows/Fonts/simhei.ttf')
words_img = wc.generate_from_frequencies(country_dict)
# 直接显示（颜色随机分配）
fig2.imshow(words_img)
# 去掉坐标轴
fig2.set_axis_off()
plt.tight_layout()
plt.show()
num1 += 1
print('第{}页爬取完毕！'.format(num1))
if num == 225:
print('爬取结束，开始写入excel。。。')
paiming = list(range(1, 251))
lst.append(paiming)
lst.append(name_lst)
lst.append(dy_lst)
lst.append(zy_lst)
lst.append(time_lst)
lst.append(country_lst)
lst.append(leixing_lst)
lst.append(pj_lst)
lst.append(people_lst)
lst.append(quote_lst)
head = ['排名', '电影名称', '导演', '主演', '年份', '地区', '类型', '评分', '评价人数', '一句简介']
ws.append(head)
for i in range(len(lst)):
for j in range(len(lst[0])):
ws.cell(j + 2, i + 1).value = lst[i][j]
print('写入excel完成！')
for cell in ws['1']:
cell.alignment = Alignment(horizontal='center', vertical='center')
for cell in ws['A']:
cell.alignment = Alignment(horizontal='center', vertical='center')
for cell in ws['B']:
cell.alignment = Alignment(horizontal='center', vertical='center')
for cell in ws['E']:
cell.alignment = Alignment(horizontal='center', vertical='center')
for cell in ws['H']:
cell.alignment = Alignment(horizontal='center', vertical='center')
for cell in ws['I']:
cell.alignment = Alignment(horizontal='center', vertical='center')
ws.column_dimensions['B'].width = 25
ws.column_dimensions['I'].width = 13
wb.save('豆瓣电影top250.xlsx')
num += 25
else:
print('失败！')
if __name__ == '__main__':
print('开始爬取！')
top250()
结果
注意
词云生成使用了背景图，如果要运行记得先更改背景图哈！附件是生成好的Excel文件，如果可以的话希望可以给点免费热心，回复回复也行呀~
[复制链接]
发表于 2020-6-23 01:35
发表于 2020-6-23 06:08
|
发表于 2020-6-23 01:52
）
