。。

抓取猫眼电影排行

 

提取猫眼电影TOP100的电影名称、时间、评分、图片等信息，提取的站点URL为，提取的结果会以文件形式保存下来。

正则：

from multiprocessing import Pool
import json
import requests
from requests.exceptions import RequestException
import re

def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 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(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('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'
')
        f.close()

def main (offset):
    url = 'http://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(offset = i * 10)
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])

#from multiprocessing import Pool
import json
import requests
from requests.exceptions import RequestException
#import re
from lxml import etree
from urllib import parse

def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 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(html):
    text = etree.HTML(html)
    node_list = text.xpath('//dl[@board-wrapper]')
    items ={}
    for node in node_list:
        index = text.xpath('./dd[@class="board-index board-index-1"]')[0].text
        image = text.xpath('./dd/img[@class="board-img"]/@src')
        title = text.xpath('./dd/p[@class="name"]/a')[0].text
        actor = text.xpath('./dd/p[@class="star"]')[0].text.strip()[3:]
        time = text.xpath('./dd/p[@class="releasetime"]')[0].text.strip()[5:]
        score = text.xpath('./dd/p[@class="score"]').text
        items = {
            'index':index,
            'image':image,
            'title':title,
            'actor':actor,
            'time': time,
            'score': score
        }
        write_to_file(items)
'''
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 {
            '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('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'
')
        f.close()

def main (offset):
    url = 'http://maoyan.com/board/4?offset='+str(offset)
    html = get_one_page(url)
    parse_one_page(html)
    #for item in parse_one_page(html):
      #  print(item)
      #  write_to_file(items)

if __name__ == '__main__':
    for i in range(10):
        main(offset = i * 10)
    #pool = Pool()
    #pool.map(main,[i*10 for i in range(10)])