爬取貓眼電影榜單的top100並輸出csv檔案
阿新 • • 發佈:2019-02-20
#!/usr/bin/env python
# -*- coding:utf-8 -*-
#encoding = utf-8
import json
import pandas as pd
import requests
from gevent.pool import Pool
from requests.exceptions import RequestException
import re
import csv
def get_one_page(url):
try:
hd = {'user-agent':'Chrome/10'}
response = requests.get(url, headers=hd)
if response.status_code==200:
return response.text
return None
except RequestException:
return None
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)
items = re.findall(pattern, html)
for item in items:
yield {
'id':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('result.txt', 'a', encoding='utf-8') as f:
f.write(json.dumps(content, ensure_ascii=False) + '\n')
def main():
con_list = []
for i in range(10):
url = 'http://maoyan.com/board/4?offset=' + str(i*10)
html = get_one_page(url)
# parse_one_page(html)
# print(html)
for item in parse_one_page(html):
con_list.append(item)
# print(item)
# write_to_file(item) #寫入到txt檔案中
print(con_list)#測試是否為[{}{}...]檔案
df = pd.DataFrame(con_list, columns=['id', 'image', 'title', 'actor', 'time', 'score'])
# print(df)# 輸出pandas結果集
df.to_csv('./myfir.csv', index=False, encoding='utf_8_sig')
if __name__ == '__main__':
main()
# for i in range(10):
# pool =Pool()
# pool.map(main, [i*10 for i in range(10)])
# 將陣列中的每個元素提取出來當作函式的引數,建立一個個程序,放進程序池中
# 第一個引數是函式,第二個引數是一個迭代器,將迭代器中的數字作為引數依次傳入函式中