抓取貓眼電影排行top100

def get_one_page(url):
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'}
response = requests.get(url,headers = headers)
if(response.status_code == 200):
return response.text
return None
def parse_one_page(html):
pattern = re.compile('<dd>.*?"board-index.*?>(.*?)</i>.*?title="(.*?)".*?data-src="(.*?)".*?"star">(.*?)</p>.*?"releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i></p>.*?</dd>',re.S)
items = re.findall(pattern,html)
for item in items:
yield {
'index':item[0],
'image': item[2],
'title': item[1].strip(),
'actor': item[3].strip(),
'time': item[4].strip(),
'score': item[5].strip() item[6].strip(),
}
def write_to_file(content):
with open('result.txt','a',encoding='utf-8')as f:
print(type(json.dumps(content)))
f.write(json.dumps(content,ensure_ascii=False) '\n')
def main(offset):
url = 'http://maoyan.com/board/4?offset=' str(offset)
html = get_one_page(url)
# print(html)
for item in parse_one_page(html):
write_to_file(item)
if __name__ == '__main__':
for i in range(10):
main(offset=i*10)