from urllib.request import urlopen
url='http://www.byhy.net/tut/auto/selenium/01/'
res=urlopen(url)
read=res.read()
print((read).decode('utf-8'))
with open('byhy.html',mode='w',encoding='utf-8') as f:
f.write((read).decode('utf-8'))
print('over')
爬取豆瓣排行
import requests
url='https://movie.douban.com/j/chart/top_list'
header={
"User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36'
}
parma={
'type': '24',
'interval_id': '100:90',
'action': '',
'start': '34',
'limit': '20',
}
res=requests.get(url=url,params=parma,headers=header)
print(res.json())
res.close()
爬取电影名字和时间 .*? 并存到CSV文件中
import re
import requests
import csv
url='https://movie.douban.com/top250'
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36'
}
res=requests.get(url,headers=headers)
pg=res.text
print(pg)
obj=re.compile(r'<li>.*?<div class="item">.*? <span class="title">(?P<name>.*?)</span>.*?<br>(?P<name2>.*?)&.*?</p>'
r'.*?<span class="rating_num" property="v:average">(?P<scores>.*?)</span>.*?<span>(?P<pingjia>.*?)</span>',re.S)
reslut=obj.finditer(pg)
f=open('data.csv',mode='w',encoding='utf-8')
csvwriter=csv.writer(f)
for it in reslut:
# print(it.group('name'))
# print(it.group('name2').strip())
# print(it.group('scores').strip())
# print(it.group('pingjia').strip())
dic=it.groupdict()
dic['name2']=dic['name2'].strip()
csvwriter.writerow(dic.values())
f.close()
print('处理完毕')
处理结果: