爬虫大作业

import requests, re, jieba,pandas
from bs4 import BeautifulSoup
from datetime import datetime
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# 获取新闻细节
def getNewsDetail(newsUrl):
    res = requests.get(newsUrl)
    res.encoding = ‘gb2312‘
    soupd = BeautifulSoup(res.text, ‘html.parser‘)
    detail = {‘title‘: soupd.select(‘#epContentLeft‘)[0].h1.text, ‘newsUrl‘: newsUrl, ‘time‘: datetime.strptime(
        re.search(‘(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})‘, soupd.select(‘.post_time_source‘)[0].text).group(1),
        ‘%Y-%m-%d %H:%M:%S‘), ‘source‘: re.search(‘来源:(.*)‘, soupd.select(‘.post_time_source‘)[0].text).group(1),
              ‘content‘: soupd.select(‘#endText‘)[0].text}
    return detail

# 通过jieba分词，获取新闻关键词
def getKeyWords():
    content = open(‘news.txt‘, ‘r‘, encoding=‘utf-8‘).read()
    wordSet = set(jieba._lcut(‘‘.join(re.findall(‘[\u4e00-\u9fa5]‘, content))))  # 通过正则表达式选取中文字符数组，拼接为无标点字符内容,再转换为字符集合
    wordDict = {}
    deleteList, keyWords = [], []
    for i in wordSet:
        wordDict[i] = content.count(i)  # 生成词云字典
    for i in wordDict.keys():
        if len(i) < 2:
            deleteList.append(i)  # 生成单字无意义字符列表
    for i in deleteList:
        del wordDict[i]  # 在词云字典中删除无意义字符
    dictList = list(wordDict.items())
    dictList.sort(key=lambda item: item[1], reverse=True)
    for dict in dictList:
        keyWords.append(dict[0])
    writekeyword(keyWords)


# 将新闻内容写入到文件
def writeNews(pagedetail):
    f = open(‘news.txt‘, ‘a‘, encoding=‘utf-8‘)
    for detail in pagedetail:
        f.write(detail[‘content‘])
    f.close()


# 将词云写入到文件
def writekeyword(keywords):
    f = open(‘keywords.txt‘, ‘a‘, encoding=‘utf-8‘)
    for word in keywords:
        f.write(‘  ‘ + word)
    f.close()

# 获取一页的新闻
def getListPage(listUrl):
    res = requests.get(listUrl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    pagedetail = []  # 存储一页所有新闻的详情
    for news in soup.select(‘#news-flow-content‘)[0].select(‘li‘):
        newsdetail = getNewsDetail(news.select(‘a‘)[0][‘href‘])  # 调用getNewsDetail()获取新闻详情
        pagedetail.append(newsdetail)
    return pagedetail


def getWordCloud():
    keywords = open(‘keywords.txt‘, ‘r‘, encoding=‘utf-8‘).read()  # 打开词云文件
    wc = WordCloud(font_path=r‘C:\Windows\Fonts\simfang.ttf‘, background_color=‘white‘, max_words=100).generate(
        keywords).to_file(‘kwords.png‘)  # 生成词云，字体设置为可识别中文字符
    plt.imshow(wc)
    plt.axis(‘off‘)
    plt.show()

pagedetail = getListPage(‘http://tech.163.com/internet/‘)  # 获取首页新闻
writeNews(pagedetail)
for i in range(2, 20):  # 因为网易新闻频道只存取20页新闻，直接设置20
    listUrl = ‘http://tech.163.com/special/tele_2016_%02d/‘ % i  # 填充新闻页，页面格式为两位数字字符
    pagedetail = getListPage(listUrl)
    writeNews(pagedetail)
getKeyWords()  # 获取词云，并且写到文件
getWordCloud()  # 从词云文件读取词云，生成词云