爬取https://www.parenting.com/baby-names/boys/earl网站top10男女生名字及相关信息
作者:互联网
爬取源代码如下:
import requestsimport bs4
from bs4 import BeautifulSoup
import re
import pandas as pd
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')
lilist=[]
r=requests.get('https://www.parenting.com/baby-names/boys/earl')
soup=BeautifulSoup(r.text,"lxml")
soup= soup.find_all('a',href=True)
for i in soup:
if 'https://www.parenting.com/pregnancy/baby-names/baby-boy-names/' in str(i)or'https://www.parenting.com/pregnancy/baby-names/girl-baby-names/' in str(i):
lilist.append(i.get("href")) lilist1=[]
results1=[]
results=[]
results2=[]
for i in list(set(lilist)):
r=requests.get(i)
soup=BeautifulSoup(r.text,"lxml")
Source=soup.find_all('p')
Source=soup.find_all(attrs={'class': 'description'})
results0 = re.findall('<h4>(.*?)</h4>', r.text)
for c in results0:
if c!='':
lilist1.append(c)
#print(lilist1)
#lilist1=[] pattern = re.compile('<p><strong>Origin:</strong>\s(.*?)</p>', re.S)
results += re.findall(pattern, str(Source))
pattern1 = re.compile('<p><strong>Meaning:</strong>\s(.*?)</p>', re.S)
results1 += re.findall(pattern1, str(Source)) pattern2 = re.compile("<p><strong>Why it’s big:</strong>\s(.*?)</p>", re.S)
results2 += re.findall(pattern2, str(Source))
print(lilist1)
print(results1)
print(results)
print(results2)
data = {
'EnName':lilist1,
'Meaning':results1,
'Origin':results,
'Description':results2
}
frame = pd.DataFrame(data)
frame.to_csv('wt10.csv',encoding="gb18030")
#print(results2)
csv文件截图:
标签:earl,www,soup,lilist1,baby,re,names,print,男女生 来源: https://www.cnblogs.com/c1q2s3/p/12078047.html