Sharing My Experience of Earning 1000 Yuan with Python

import pandas as pd
import numpy as np
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
# get_ipython().run_line_magic('matplotlib', 'inline')

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2021年06月05日
# @File    : demo4.py
import requests
from fake_useragent import UserAgent
from lxml import etree
import time

# Random request header
ua = UserAgent()

# Build request. You need to refresh the webpage if you can't get a response.
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',    'Cookie': '__mta=244176442.1622872454168.1622876903037.1622877097390.7; uuid_n_v=v1; uuid=6FFF6D30C5C211EB8D61CF53B1EFE83FE91D3C40EE5240DCBA0A422050B1E8C0; _csrf=bff9b813020b795594ff3b2ea3c1be6295b7453d19ecd72f8beb9700c679dfb4; Hm_lvt_703e94591e87be68cc8da0da7cbd0be2=1622872443; _lxsdk_cuid=1770e9ed136c8-048c356e76a22b-7d677965-1fa400-1770e9ed136c8; _lxsdk=6FFF6D30C5C211EB8D61CF53B1EFE83FE91D3C40EE5240DCBA0A422050B1E8C0; ci=59; recentCis=59; __mta=51142166.1622872443578.1622872443578.1622876719906.2; Hm_lpvt_703e94591e87be68cc8da0da7cbd0be2=1622877097; _lxsdk_s=179dafd56bf-06d-403-d81%7C%7C12',    'User-Agent': str(ua.random)}

def RequestsTools(url):    '''    Crawler request tool function    :param url: request address    :return: HTML object for xpath extraction    '''    response = requests.get(url, headers=headers).content.decode('utf-8')    html = etree.HTML(response)    return html

def Index(page):    '''    Homepage function    :param page: page number    :return:    '''    url = 'https://maoyan.com/board/4?offset={}'.format(page)    html = RequestsTools(url)    # Detail page address suffix    urls_text = html.xpath('//a[@class="image-link"]/@href')    # Rating    pingfen1 = html.xpath('//i[@class="integer"]/text()')    pingfen2 = html.xpath('//i[@class="fraction"]/text()')
    for i, p1, p2 in zip(urls_text, pingfen1, pingfen2):        pingfen = p1 + p2        urs = 'https://maoyan.com' + i        # Avoid too frequent requests        time.sleep(2)        Details(urs, pingfen)

def Details(url, pingfen):    html = RequestsTools(url)    dianyan = html.xpath('//h1[@class="name"]/text()') # Movie name    leixing = html.xpath('//li[@class="ellipsis"]/a/text()') # Genre    diqu = html.xpath('/html/body/div[3]/div/div[2]/div[1]/ul/li[2]/text()') # Read total    timedata = html.xpath('/html/body/div[3]/div/div[2]/div[1]/ul/li[3]/text()') # Time    for d, l, b, t in zip(dianyan, leixing, diqu, timedata):        countyr = b.replace('\n', '').split('/')[0] # Location        shichang = b.replace('\n', '').split('/')[1] # Duration        f = open('猫眼.csv', 'a')        f.write('{}, {}, {}, {}, {}, {}, {}
'.format(d, pingfen, url, l, countyr, shichang, t))        print(d, pingfen, url, l, countyr, shichang, t )

for page in range(0, 11):    page *= 10    Index(page)

#!/usr/bin/env python
# coding: utf-8
# Load commonly used data analysis libraries
import pandas as pd
import numpy as np
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
# get_ipython().run_line_magic('matplotlib', 'inline')

# In[3]:

path='./maoyan.csv'
df=pd.read_csv(path,sep=',',encoding='utf-8',index_col=False)
df.drop(df.columns[0],axis=1,inplace=True)
df.dropna(inplace=True)
df.drop_duplicates(inplace=True)
df.head(10)


# Check the structure of the data
df.info()
print(df.columns)

# In[11]:

# Year & Number of Movies Released
# The number of releases after 2018 is uncertain, so we will exclude them for now
fig,ax=plt.subplots(figsize=(9,6),dpi=70)
df[df[u'上映时间']<2018][u'上映时间'].value_counts().sort_index().plot(kind='line',ax=ax)
ax.set_xlabel(u'Year')
ax.set_ylabel(u'Number of Releases')
ax.set_title(u'Release Year & Number of Movies Released')


# Based on the above, create another graph showing the relationship between release year & number of releases & ratings
# However, since the data before 1980 is sparse and the ratings are inaccurate, we will focus on the analysis from 1980-2017
x=df[df[u'上映时间']<2018][u'上映时间'].value_counts().sort_index().index
y=df[df[u'上映时间']<2018][u'上映时间'].value_counts().sort_index().values
y2=df[df[u'上映时间']<2018].sort_values(by=u'上映时间').groupby(u'上映时间').mean()[u'评分'].values
fig,ax=plt.subplots(figsize=(10,5),dpi=70)
ax.plot(x,y,label=u'Number of Releases')
ax.set_xlim(1980,2017)
ax.set_xlabel(u'Release Year')
ax.set_ylabel(u'Number of Releases')
ax.set_title(u'Release Year & Number of Releases & Average Ratings')
ax2=ax.twinx()
ax2.plot(x,y2,c='y',ls='--',label=u'Ratings')
ax.legend(loc=1)
ax2.legend(loc=2)

# Solve Chinese character display issues and prevent negative values on axes
plt.rcParams['font.sans-serif'] =['Microsoft YaHei']
plt.rcParams['axes.unicode_minus'] = False

# In[12]:

# World & Release Year & Average Ratings
fig,ax=plt.subplots(figsize=(10,7),dpi=60)
df[df[u'评分']>0].groupby(u'上映时间').mean()[u'评分'].plot(kind='line',ax=ax)
ax.set_ylabel(u'Ratings')
ax.set_title(u'World & Release Year & Average Ratings')

# In[13]:

# Number of Movies by Genre Worldwide
# Split genres into smallest units and count

types=[]
for tp in df[u'类型']:
    ls=tp.split(',')
    for x in ls:
        types.append(x)


# Create DataFrame for genre counts

tp_df=pd.DataFrame({u'类型':types})
fig,ax=plt.subplots(figsize=(9,6),dpi=60)
tp_df[u'类型'].value_counts().plot(kind='bar',ax=ax)
ax.set_xlabel(u'Genre')
ax.set_ylabel(u'Count')
ax.set_title(u'World & Genre & Count')

# In[14]:

# Distribution of Movie Duration & Ratings
# There’s an issue: some movies have not been rated, so we need to exclude those
x=df[df[u'评分']>0].sort_values(by=u'时长(min)')[u'时长(min)'].values
y=df[df[u'评分']>0].sort_values(by=u'时长(min)')[u'评分'].values
fig,ax=plt.subplots(figsize=(9,6),dpi=70)
ax.scatter(x,y,alpha=0.6,marker='o')
ax.set_xlabel(u'Duration (min)')
ax.set_ylabel(u'Count')
ax.set_title(u'Distribution of Movie Duration & Ratings')

# We can see the ratings

# In[25]:

dfs=df[(df[u'上映时间']>1980)&(df[u'上映时间']<2019)]


# for x in range(0,len(dfs)):#     print(dfs.iat[x,0],dfs.iat[x,-1])
df666 = dfs['电影'][:15]
wl = ",".join(df666.values)
# Write the segmented text to a file
# fenciTxt  = open("fenciHou.txt","w+")# fenciTxt.writelines(wl)# fenciTxt.close()
# Set up word cloud
lwc = WordCloud(background_color="white",  # Set background color               # mask=imread('shen.jpg'),   # Set background image#                    max_words=2000,  # Set maximum number of words                   font_path="C:\Windows\Fonts\simkai.ttf", # Set font to KaiTi Regular    # Set Chinese font so that the word cloud can display (the default font does not support Chinese)
               max_font_size=60, # Set maximum font size               random_state=30,  # Set how many random generation states, i.e., how many color schemes               )
myword = wc.generate(wl)  # Generate word cloud
wc.to_file('result.jpg')
# Display word cloud
plt.imshow(myword)
plt.axis("off")
plt.show()

# In[41]: