1.取出一個新聞列表頁的全部新聞 包裝成函數。

2.獲取總的新聞篇數，算出新聞總頁數。

3.獲取全部新聞列表頁的全部新聞詳情。

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


# 獲取新聞點擊次數
def getNewsId(url):
    newsId = re.findall(r‘\_(.*).html‘, url)[0][-4:]
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newsId)
    clickRes = requests.get(clickUrl)
    # 利用正則表達式獲取新聞點擊次數
    clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", clickRes.text).group(1))
    return clickCount


# 獲取新聞細節
def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)

    content = soupd.select(‘#content‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    # 調用getNewsId()獲取點擊次數
    count = getNewsId(newsUrl)
    # 識別時間格式
    date = re.search(‘(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})‘, info).group(1)
    # 識別一個至三個數據
    if(info.find(‘作者：‘)>0):
        author = re.search(‘作者：((.{2,4}\s|.{2,4}、){1,3})‘, info).group(1)
    if(info.find(‘審核：‘)>0):
        check = re.search(‘審核：((.{2,4}\s){1,3})‘, info).group(1)
    if(info.find(‘來源：‘)>0):
        sources = re.search(‘來源：(.*)\s*攝|點‘, info).group(1)
    # 用datetime將時間字符串轉換為datetime類型
    dateTime = datetime.strptime(date, ‘%Y-%m-%d %H:%M:%S‘)
    # 利用format對字符串進行操作
    print(‘發布時間：{0}\n作者：{1}\n審核：{2}\n來源：{3}\n點擊次數：{4}‘.format(dateTime, author, check, sources, count))
    print(content)

# 獲取列表頁新聞
def getListPage(listUrl):
    res = requests.get(listUrl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)

    for new in soup.select(‘li‘):
        if len(new.select(‘.news-list-title‘)) > 0:
            title = new.select(‘.news-list-title‘)[0].text
            description = new.select(‘.news-list-description‘)[0].text
            newsUrl = new.select(‘a‘)[0][‘href‘]

            print(‘標題:{0}\n內容:{1}\n鏈接:{2}‘.format(title, description, newsUrl))
            # 調用getNewsDetail()獲取新聞詳情
            getNewsDetail(newsUrl)
            break

# 獲取新聞總頁數
def getListTotalNumber(firstUrl):
    res = requests.get(firstUrl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    listCount = int(soup.select(‘.a1‘)[0].text.rstrip(‘條‘)) // 10 + 1
    return listCount

firstUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
getListPage(firstUrl)
# 獲取新聞總頁數
n=getListTotalNumber(firstUrl)

for i in range(2,n):
    listUrl= ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    getListPage(listUrl)

4.找一個自己感興趣的主題，進行數據爬取，並進行分詞分析。不能與其它同學雷同。

import requests
from bs4 import BeautifulSoup

# 獲取新聞細節
def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)
    content = soupd.select(‘.cont‘)[0].text.rsplit("復仇者聯盟2：奧創紀元下載地址:http://www.80smp4.net/mp4_3gp/26733/")[0]
    print(‘內容:{}‘.format(content))

# 獲取列表頁新聞
def getListPage(listUrl):
    res = requests.get(listUrl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)

    for new in soup.select(‘div‘):
        if len(new.select(‘.ph_u‘)) > 0:
            description = new.select(‘.title‘)[0].text.split()[0]
            newsUrl = new.select(‘a‘)[0][‘href‘]
            # print(‘標題:{0}\n內容:{1}\n鏈接:{2}‘.format(title, description, newsUrl))
            # 調用getNewsDetail()獲取新聞詳情
            print(‘片名:{0}\n連接:{1}‘.format(description,newsUrl))
            getNewsDetail(newsUrl)
            break

firstUrl = ‘http://www.80smp4.net/movie/‘
getListPage(firstUrl)

爬取基礎2