爬取猫眼小demo
import json
import time
import requests
from requests.exceptions import RequestException
from lxml import etree
def get_one_page(url):
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
try:
response =requests.get(url,headers=headers)
if response.status_code==200:
return response.text
return None
except RequestException:
return None
def parse_one_page(page_sourse):
html = etree.HTML(page_sourse)
movie_list = html.xpath('//dl[@class="board-wrapper"]//dd')
movies=[]
for movie in movie_list:
info= {
'index':movie.xpath('./i/text()')[0],
'image':movie.xpath('./a/img[2]/@data-src')[0],
'title':movie.xpath('.//p[@class="name"]/a/text()')[0],
'actor':movie.xpath('.//p[@class="star"]/text()')[0].strip(),
'time':movie.xpath('.//p[@class="releasetime"]/text()')[0],
'score':''.join(movie.xpath('.//p[@class="score"]/i/text()'))
}
movies.append(info)
print(info)
return movies
def write_to_json(movies):
with open('result.txt','a') as f:
for movie in movies:
info = json.dumps(movie,ensure_ascii=False)
f.write(info+'\n')
def main(offset):
url = 'http://maoyan.com/board/4?offset=' +str(offset)
page_sourse =get_one_page(url)
movies = parse_one_page(page_sourse)
write_to_json(movies)
if __name__ == '__main__':
for i in range(5):
main(offset=i*10)
time.sleep(2)