爬取貓眼電影top100

先獲取首頁的源代碼

def get_one_page(url):
    try:
        headers={
            'User-Agent':'Mozilla/5.0(Macintosh;intel Mac OS 10_11_4)Applewebkit/537.36(KHTML,like Gecko)Chrome/52.0.2743.116 Safari/537.36'
        }
        re=requests.get(url,headers=headers)
        if re.status_code==200:
            return re.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    pattern=re.compile('<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?class="name".*?">(.*?)</a>.*?class="star">(.*?)</p>.*?releasetime.*?>(.*?)</p>',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:]
        }

def save_one_page(content):
    with open('re.txt','a',encoding='utf8')as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content,ensure_ascii=False)+'\n')
def main(offest):
    url = ('https://maoyan.com/board/4?offset='+str(offest))
    html = get_one_page(url)
    for item in parse_one_page(html):
        save_one_page(item)

if __name__ == '__main__':
       for i in range(10):
           main(offest=i*10)

結果