爬虫大作业

Posted 2020-11-01 123-王展洪

1.爬取豆瓣电影top250。(所有同学不能雷同)

2.用python 编写爬虫程序，从网络上爬取相关主题的数据。

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
import pandas

# 电影简介保存到txt。
def writeNewsDetail(content):
    f = open(\'wzh.txt\', \'a\',encoding=\'utf-8\')#文件名、打开方式
    f.write(content)#写入
    f.close()#关闭文件

#电影的简介
def getMovieDetail(url):
    resd = requests.get(url)
    resd.encoding = \'utf-8\'
    soupd = BeautifulSoup(resd.text, \'html.parser\')
    movies={}
    if (int(len(soupd.select(\'#link-report\'))) > 0):
        movies[\'content\'] = soupd.select(\'#link-report\')[0].text
    else:
        movies[\'content\'] =\'none\'
    if (int(len(soupd.select(\'.attrs\'))) > 0):
        movies[\'director\'] = soupd.select(\'.attrs\')[0].text
    else:
        movies[\'director\']=\'none\'
    if (int(len(soupd.select(\'.actor a\'))) > 0):
        movies[\'actor\'] = soupd.select(\'.actor a\')[0].text
    else:
        movies[\'actor\'] = \'none\'
    if(int(len(soupd.select(\'h1\')))>0):
        movies[\'name\']=soupd.select(\'h1\')[0].text
    else:
        movies[\'name\'] = \'none\'
    if(int(len(soupd.select(\'strong\'))) > 0):
        movies[\'score\'] = soupd.select(\'strong\')[0].text
    else:
        movies[\'score\'] =\'none\'
    movies[\'url\'] = url
    return (movies)

# 电影列表页的总页数
def getPageN(url):
    res = requests.get(url)
    res.encoding = \'utf-8\'
    soup = BeautifulSoup(res.text, \'html.parser\')
    #num = soup.select(\'.paginator a\')[-2].text
    print(\'列表页数：\',num)

#一个列表页全部电影
def getListPage(url):
    res = requests.get(url)
    res.encoding = \'utf-8\'
    soup = BeautifulSoup(res.text, \'html.parser\')
    moviesList = []
    urls = soup.select(\'.hd a\')
    # for i in range(10):
    #     if(i==0)
    #     urls=\'htthttps://movie.douban.com/top250?start=25&filter=\'
    for j in range(int(len(urls))):
        url = soup.select(\'.hd a\')[j].attrs[\'href\']
        moviesList.append(getMovieDetail(url))#在列表末尾添加新的对象
    return (moviesList)

moviesTotal = []
Url = \'https://movie.douban.com/top250?start=0&filter=\'
moviesTotal.extend(getListPage(Url))  # 在列表末尾一次性追加另一个序列中的多个值（用新列表扩展原来的列表）
getPageN(Url)
dt =pandas.DataFrame(moviesTotal)
dt.to_excel("wzh.xlsx")
print(dt)

 

3.对爬了的数据进行文本分析，生成词云。

import jieba.analyse
from PIL import Image,ImageSequence
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud,ImageColorGenerator
lyric= \'\'
f=open(\'wzh.txt\',\'r\',encoding=\'utf-8\')
for i in f:
    lyric+=f.read()


result=jieba.analyse.textrank(lyric,topK=50,withWeight=True)
keywords = dict()
for i in result:
    keywords[i[0]]=i[1]
print(keywords)


image= Image.open(\'tim.png\')
graph = np.array(image)
wc = WordCloud(font_path=\'./fonts/simhei.ttf\',background_color=\'Green\',max_words=50,mask=graph)
wc.generate_from_frequencies(keywords)
image_color = ImageColorGenerator(graph)
plt.imshow(wc)
plt.imshow(wc.recolor(color_func=image_color))
plt.axis("off")
plt.show()
wc.to_file(\'dream.png\')

4.对文本分析结果进行解释说明。

对于爬虫结果，我们可以看出评分高的电影有哪些类型，哪些导演的电影作品比较好看，哪些演员演得电影比较出名，哪些年代的电影比较受欢迎

 

5.写一篇完整的博客，描述上述实现过程、遇到的问题及解决办法、数据分析思想及结论。

问题：没有爬出完整的top250de 电影，使用for循环，10个列表页逐个提取

PyCharm中导入wordcloud是出错，没生成词云统计图

 

6.最后提交爬取的全部数据、爬虫及数据分析源代码。