python写采集程序_python，利用BeautifulSoup写的第一采集程序

import requests

from bs4 import BeautifulSoup

link="http://www.xiangmingshan.com/zhishi/"

headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}

r=requests.get(link,headers=headers)

soup=BeautifulSoup(r.text, "lxml")

titles=soup.find_all("h3", class_="f-16 mb15 f-bold")

i=0

for title in titles:

i+=1

print(i,title.text)

urlnames=title.a

url=urlnames.get('href')

res=requests.get(url,headers=headers)

conaa=BeautifulSoup(res.text,"lxml")

neirong=conaa.find(class_="info-con")

print("正文内容：",neirong.text)import requests

from bs4 import BeautifulSoup

link="http://www.xiangmingshan.com/zhishi/"

headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}

r=requests.get(link,headers=headers)

soup=BeautifulSoup(r.text, "lxml")

titles=soup.find_all("h3", class_="f-16 mb15 f-bold")

i=0

for title in titles:

i+=1

print(i,title.text)

url=title.a['href']

res=requests.get(url,headers=headers)

conaa=BeautifulSoup(res.text,"lxml")

neirong=conaa.find(class_="info-con")

print("正文内容：",neirong.text)

其中获取链接有两个不同方式，分别是url=urlnames.get('href')

与url=title.a['href']