Python使用asyncio+aiohttp异步爬取猫眼电影专业版

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

import asyncio

from aiohttp import ClientSession

import aiohttp

import time

import csv

import ssl

ssl._create_default_https_context = ssl._create_unverified_context

headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) ‘

                             ‘AppleWebKit/537.36 (KHTML, like Gecko) ‘

                             ‘Chrome/67.0.3396.99 Safari/537.36‘}

# 协程函数，完成一个无阻塞的任务

async def get_one_page(url):

    try:

        conn = aiohttp.TCPConnector(verify_ssl=False)  # 防止ssl报错

        async with aiohttp.ClientSession(connector=conn) as session:  # 创建session

            async with session.get(url, headers=headers) as r:

                # 返回解析为字典的电影数据

                return  await r.json()

    except Exception as e:

        print(‘请求异常： ‘ + str(e))

        return {}

# 解析函数，提取每一条内容并写入csv文件

def parse_one_page(movie_dict, writer):

    try:

        movie_list = movie_dict[‘data‘][‘list‘]

        for movie in movie_list:

            movie_name = movie[‘movieName‘]

            release = movie[‘releaseInfo‘]

            sum_box = movie[‘sumBoxInfo‘]

            box_info = movie[‘boxInfo‘]

            box_rate = movie[‘boxRate‘]

            show_info = movie[‘showInfo‘]

            show_rate = movie[‘showRate‘]

            avg_show_view = movie[‘avgShowView‘]

            avg_seat_view = movie[‘avgSeatView‘]

            writer.writerow([movie_name, release, sum_box, box_info, box_rate,

                            show_info, show_rate, avg_show_view, avg_seat_view])

        return(‘写入成功‘)

    except Exception as e:

        return(‘解析异常： ‘ + str(e))

# 并发爬取

async def main():

    # 待访问的20个URL链接

    urls = [‘https://box.maoyan.com/promovie/api/box/second.json?beginDate=201904{}{}‘.format(i, j) for i in range(1, 3) for j in range(10)]

    # 任务列表

    tasks = [get_one_page(url) for url in urls]

    # 并发执行并保存每一个任务的返回结果

    results = await asyncio.gather(*tasks)

    # 处理每一个结果

    with open(‘pro_info.csv‘, ‘w‘) as f:

        writer = csv.writer(f)

        for result in results:

            print(parse_one_page(result, writer))

if __name__ == "__main__":

    start = time.time()

    # asyncio.run(main())

    # python3.7之前的写法

    loop = asyncio.get_event_loop()

    loop.run_until_complete(main())

    loop.close()

    print(time.time()-start)