爬虫大作业

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

# 将标签内容写入文件
def writeNewsDetail(tag):
    f=open('dongman.txt','a',encoding='utf-8')
    f.write(tag)
    f.close()
# 获取总页数
def getPage(PageUrl):
    res = requests.get(PageUrl)
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")
    n = soup.select(".main .pages a")[-2].text
    print(n)
    return int(n)

# 获取全部页码链接
def getgain(PageNumber):
    for i in range(1,PageNumber+1):
        NeedUrl = 'http://www.kisssub.org/sort-1-{}.html'.format(i)
        print(NeedUrl)
        # 获取单个页面页面所有链接
        getList(NeedUrl)
        # getinformation(NeedUrl)

# 获取单个页面页面所有链接
def getList(Url):
    res = requests.get(Url)
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")
    # 获取单个页面所有的资源链接
    page_url = soup.select('td[style="text-align:left;"] a')
    # 将获得的资源链接进行单个输出，然后获取链接的页面信息
    for i in page_url:
        listurl = 'http://www.kisssub.org/' + i.get('href')
        print(listurl)
        getinformation(listurl)

    return listurl
# 获取页面的信息
def getinformation(url):
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    # 获取标题
    title = soup.select(".location a")[-1].text
    print("标题：",title)
    # 获取时间
    times = soup.select(".basic_info p")[3].text
    time = times.lstrip('发布时间:')[:20].strip()

    print("时间：",time)

    # 获取发布者
    publishs = soup.select(".basic_info p")[0].text.strip()
    publish = publishs.lstrip('发布代号: ')[:20]
    print("发布者",publish)

    # 获取下载数量
    downloads = soup.select(".basic_info p")[4].text.strip()
    a = re.match(".*?下载(.*),",downloads)
    download = a.group(1).strip()
    print("下载数量：",download)

    #获取标签
    tags = soup.select(".box .intro")[1].text.replace("
 ", "")
    tag =tags.replace(" ", "")
    # # tags = soup.select(".box .intro")[1].text.strip("")
    print("标签：",tag)
    writeNewsDetail(tag)

# 生成词云
def getWord():
    lyric = ''
    # 打开文档，进行编译，防止错误
    f = open('dongman.txt', 'r', encoding='utf-8')
    # 将文档里面的数据进行单个读取，便于生成词云
    for i in f:
        lyric += f.read()
    #     进行分析
    result = jieba.analyse.textrank(lyric, topK=50, withWeight=True)
    keywords = dict()
    for i in result:
        keywords[i[0]] = i[1]
    print(keywords)

    # 获取词云生成所需要的模板图片
    image = Image.open('tim.jpg')
    graph = np.array(image)
    # 进行词云的设置
    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('dream.png')
PageUrl = 'http://www.kisssub.org/sort-1-1.html'

PageNumber = getPage(PageUrl)
getgain(PageNumber)
getWord()

首先设置好几个函数，分别是获取总的页面个数、获取全部页码链接、页面信息展示、获取页面所有链接，大致定义好四个，在编写获得单个页面所有链接出了点问题，最后发现是soup没有弄好，
接下来就是进行词云生成，为了方便，我将收集到的标签信息用TXT格式保存，然后进行词云分析、生成。
这次爬取的是一个动漫资源网站，将网站里面的标题、时间、发布者、下载数量还有标签全部爬取，生成的词云也以标签为标准进行生成