1. 将新闻的正文内容保存到文本文件。
def writeNewsDetails(contents): f = open('gzccnews.txt', 'a', encoding='utf-8') f.write(contents) f.close()
2. 将新闻数据结构化为字典的列表:
- 单条新闻的详情-->字典news
- 一个列表页所有单条新闻汇总-->列表newsls.append(news)
- 所有列表页的所有新闻汇总列表newstotal.extend(newsls)
def
getClickCount(newsUrl):
newId
=
re.search(
'\_(.*).html'
, newsUrl).group(
1
).split(
'/'
)[
-
1
]
res
=
requests.get(
'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'
.
format
(newId))
res.encoding
=
'utf-8'
count
=
int
(res.text.split(
'.html'
)[
-
1
].lstrip(
"('"
).rstrip(
"');"
))
return
count
def
getNewDetail(newsUrl):
res
=
requests.get(newsUrl)
res.encoding
=
'utf-8'
soup
=
BeautifulSoup(res.text,
'html.parser'
)
news
=
{}
news[
'title'
]
=
soup.select(
'.show-title'
)[
0
].text
# info = soup.select('.show-info')[0].text.split()
info
=
soup.select(
'.show-info'
)[
0
].text
content
=
soup.select(
'#content'
)[
0
].text
# writeFile(content)
# print(soup.select('#content')[0].text)
s
=
info.split()[
0
].lstrip(
'发布时间:'
)
+
" "
+
info.split()[
1
]
# 发布时间
# zz = info[2].lstrip('作者:') #作者
# sh = info[3].lstrip('审核:') #审核
# ly = info[4].lstrip("来源:") #来源
if
info.find(
'来源:'
) >
0
:
news[
'source'
]
=
info[info.find(
'来源:'
):].split()[
0
].lstrip(
'来源:'
)
else
:
news[
'source'
]
=
'none'
news[
'time'
]
=
datetime.strptime(s,
'%Y-%m-%d %H:%M:%S'
)
news[
'clickCount'
]
=
getClickCount(newsUrl)
news[
'newsUrl'
]
=
newsUrl
# print(cc,type(cc))
print
(news)
return
news
def
getListPage(pageUrl):
res
=
requests.get(pageUrl)
res.encoding
=
'utf-8'
soup
=
BeautifulSoup(res.text,
'html.parser'
)
newslist
=
[]
for
news
in
soup.select(
'li'
):
if
len
(news.select(
'.news-list-title'
)) >
0
:
a
=
news.select(
'a'
)[
0
].attrs[
'href'
]
# URL
newslist.append(getNewDetail(a))
return
newslist
def
getPageN():
res
=
requests.get(
'http://news.gzcc.cn/html/xiaoyuanxinwen/'
)
res.encoding
=
'utf-8'
soup
=
BeautifulSoup(res.text,
'html.parser'
)
pagenumber
=
int
(soup.select(
'.a1'
)[
0
].text.rstrip(
'条'
))
page
=
pagenumber
/
/
10
+
1
return
page
print
(getPageN())
firstUrl
=
'http://news.gzcc.cn/html/xiaoyuanxinwen'
res
=
requests.get(firstUrl)
res.encoding
=
'utf-8'
n
=
getPageN()
newstotal
=
[]
for
i
in
range
(
2
,
4
):
print
(i)
listPageUrl
=
'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'
.
format
(i)
temp
=
getListPage(listPageUrl)
newstotal.extend(temp)
3. 安装pandas,用pandas.DataFrame(newstotal),创建一个DataFrame对象df.
df = pandas.DataFrame(newsTotal) print(df)
4. 通过df将提取的数据保存到csv或excel 文件。
df.to_csv('gzccnews.csv') df.to_excel('gzccnews.xlsx')
5. 用pandas提供的函数和方法进行数据分析:
- 提取包含点击次数、标题、来源的前6行数据
- 提取‘学校综合办’发布的,‘点击次数’超过3000的新闻。
- 提取'国际学院'和'学生工作处'发布的新闻。
- 进取2018年3月的新闻
print(df[['title','clickCount','source']][:6]) print(df[(df['clickCount']>3000)&(df['source']=='学校综合办')]) sou = ['国际学院','学生工作处'] print(df[df['source'].isin(sou)]) # 进取2018年3月的新闻 df1 = df.set_index('time') print(df1['2018-03'])
6. 保存到sqlite3数据库
import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
df3.to_sql('gzccnews05',con = db, if_exists='replace')
import sqlite3 with sqlite3.connect('gzccnewsdb.sqlite') as db: df3.to_sql('gzccnews05',con = db, if_exists='replace')
7. 从sqlite3读数据
with sqlite3.connect('gzccnewsdb.sqlite') as db:
df2 = pandas.read_sql_query('SELECT * FROM gzccnews05',con=db)
print(df2)
with sqlite3.connect('gzccnewsdb.sqlite') as db: df2 = pandas.read_sql_query('SELECT * FROM gzccnews05',con=db) print(df2)
8. df保存到mysql数据库
安装SQLALchemy
安装PyMySQL
MySQL里创建数据库:create database gzccnews charset utf8;
import pymysql
from sqlalchemy import create_engine
conn = create_engine('mysql+pymysql://root:root@localhost:3306/gzccnews?charset=utf8')
pandas.io.sql.to_sql(df, 'gzccnews', con=conn, if_exists='replace')
MySQL里查看已保存了数据。(通过MySQL Client或Navicate。)