爬虫大作业

Posted 2020-11-01 098-谢家豪

import requests
import re
from bs4 import BeautifulSoup
import jieba.analyse
from PIL import Image, ImageSequence
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud, ImageColorGenerator

# 获取总页数
def getnum(url):
    res = requests.get(url)
    res.encoding = \'gb2312\'
    soup = BeautifulSoup(res.text, \'html.parser\')
    Info = soup.select(".page-next")[0].extract().text
    TotalNum = re.search("共(\\d+)页.*",Info).group(1)
    return TotalNum

#获取单个页面所有链接
def getpageurl(url):
    res = requests.get(url)
    res.encoding = \'gb2312\'
    soup = BeautifulSoup(res.text, \'html.parser\')
    a = soup.select(".list-page ul")
    for i in soup.select(".list-page ul li"):
        if len(i.select("a"))>0:
            info = i.select("a")[0].attrs[\'href\']
            pageurl = \'http://www.ckck.tv/\' + info
            print(pageurl)
            getinfromation(pageurl)
# 获取页面的信息
def getinfromation(url):
    res = requests.get(url)
    res.encoding = \'gb2312\'
    soup = BeautifulSoup(res.text, \'html.parser\')
    a = soup.select(".content .movie ul h1")[0].text
    print("电影：",a)
    b = soup.select(".content .movie ul li")[1].text
    name = re.search("【主　演】：(.*)",b).group(1)
    print("主演:",name)
    c = soup.select(".content .movie ul li")[4].text
    date = re.search("【年　代】：(.*)  【地　区】：", c).group(1)
    print("年代：", date)
    diqu = re.search("【地　区】：(.*)", c).group(1)
    print("地区：",diqu)
    # 将标签内容写入文件
    f = open(\'gzccNews.txt\', \'a\', encoding=\'utf-8\')
    f.write(a )
    f.write(name )
    f.write(date )
    f.write(diqu)
    f.write("\\n")
    f.close()

# 生成词云
def getpicture():
    lyric = \'\'
    f = open(\'gzccNews.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(\'input.jpg\')
    graph = np.array(image)
    wc = WordCloud(font_path=\'./fonts/simhei.ttf\', background_color=\'White\', 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(\'output.png\')


url = \'http://www.ckck.tv/xj/Index.html\'
a = getnum(url)
getpageurl(url)
for i in range(2,int(a)):
     page = \'http://www.ckck.tv/xj/List_4_{}.html\'.format(i)
     getpageurl(page)
getpicture()

首先定义获取总页面、获取页面所有链接、获取页面信息、生成词云等的函数，过程中就是获取所有页面所有链接出现点问题，归结于找标签问题。这次爬取的是一个电影网站，将网站里面的电影名、主演、年代、地区，然后进行词云生成