1.導(dǎo)入需要的庫
import requests
import re
import json
from requests.exceptions import RequestException
2.定義一個網(wǎng)頁抓取函數(shù)
def get_one_page(url):
try : # 異常處理
response=requests.get(url)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
3.定義一個網(wǎng)頁解析函數(shù)
def parse_one_page(html):
pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
+'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
+'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S) #正則表達式解析HTML
items=re.findall(pattern,html)
for item in items:
yield {
'index':item[0],
'image':item[1],
'title':item[2],
'actor':item[3].strip()[3:],
'time':item[4].strip()[5:],
'score':item[5]+item[6]
}
4.把得到的數(shù)據(jù)存儲到文檔中
def write_to_file(content):
with open('result.txt','a',encoding='utf-8') as f:
f.write(json.dumps(content,ensure_ascii=False) +'\n')
f.close()
#參數(shù)encoding和ensure_ascii使得中文正常顯示
5.調(diào)用以上函數(shù)羊娃，完成一個數(shù)據(jù)抓取過程
def main(offset):
url = 'https://maoyan.com/board/4?offset='+ str(offset)
html = get_one_page(url)
for item in parse_one_page(html):
print(item)
write_to_file(item)
if __name__ == '__main__':
for i in range(10):
main(i*10) #設(shè)置網(wǎng)頁URL遞推，實現(xiàn)多個網(wǎng)頁一次抓取
6.得到存儲數(shù)據(jù)的文檔
抓取數(shù)據(jù)前十行
