Python爬取猫眼电影top100榜
1. 爬取TOP100所有电影的信息,(电影名, 主演， 上映时间)
2. 爬取该电影的宣传封面的图片, 保存到本地/mnt/img/目录中;
3. 将获取的信息, 保存到mysql数据库中(电影名, 主演， 上映时间, 封面图片的本地路径)
（部分功能没有实现）
import re
import jsonfrom multiprocessing.pool import Pool
from requests.exceptions import RequestException
import urllib.request
def get_page(url):
try:
req = urllib.request.Request(url)
headers = {'User-agent': 'FireFox/12.0'}
response = urllib.request.urlopen(req)
html = response.read().decode('utf-8')
if html != None:
return html
return None
except RequestException:
return None
def parse_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)
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]
}
def write_to_file(content):
with open('Movies.txt', 'a', encoding='utf-8') as f:
f.write(json.dumps(content, ensure_ascii=False) + '\n')
f.close()
def main(num):
url = 'http://maoyan.com/board/4?offset=' + str(num)
html = get_page(url)
for item in parse_page(html):
print(item)
write_to_file(item)
if __name__ == '__main__':
pool = Pool()
pool.map(main, [i * 10 for i in range(10)])