网页新闻爬虫

1.结构化：

• 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)

2.转换成pandas的数据结构DataFrame

3.从DataFrame保存到excel

4.从DataFrame保存到sqlite3数据库

 

from bs4 import BeautifulSoup
from datetime import datetime
import requests
import re
import pandas
import sqlite3

def getclick(url):
    m=re.search(r'_(.*).html',url)
    newsid =m.group(1)[5:]
    clickurl="http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsid)
    resc=requests.get(clickurl).text
    r=re.search(r"hits(.*)",resc).group(1)
    click=r.lstrip("').html('").rstrip("');")
    click=int(click)
    return(click)

def getdetail(url):
    resd = requests.get(url)
    resd.encoding="utf-8"
    soupd = BeautifulSoup(resd.text,"html.parser")
    news ={}
    news['net']=url
    news['title']=soupd.select(".show-title")[0].text
    info=soupd.select('.show-info')[0].text
    news['source']=re.search('来源：(.*)点击',info).group(1).strip()
    news['content']=soupd.select(".show-content")[0].text.strip()
    news['click']=getclick(url)
    return(news)

def onepage(pageurl):    
    res = requests.get(pageurl)
    res.encoding="utf-8"
    soup = BeautifulSoup(res.text,"html.parser")
    newsls=[]
    for news in soup.select("li"):
        if len(news.select(".news-list-title"))>0:
            newsls.append(getdetail(news.select('a')[0]["href"]))
    return(newsls)

newstotal=[]
gzccurl="http://news.gzcc.cn/html/xiaoyuanxinwen/"
newstotal.extend(onepage(gzccurl))

res = requests.get(gzccurl)
res.encoding="utf-8"
soup = BeautifulSoup(res.text,"html.parser")
n=int(soup.select('.a1')[0].text.rstrip("条"))
pages=n//10+1

for i in range(2,3):
    listurl="http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
    newstotal.extend(onepage(listurl))

df = pandas.DataFrame(newstotal)
print(df.head())

with sqlite3.connect('gzccnewsdb2.sqlite') as db:
    df.to_sql('gzccnewsdb2',con= db )