result=re.findall(pattern,html)
for i in result:
yield{
"index":i[0],
"title": i[1],
"image":i[2],
"actor":i[3].strip(),
"time":i[4][5:],
"score":i[5]+i[6]
}
def write_to_txt(content):
with open("maoyan.txt","a",encoding="utf-8")as f:
f.write(json.dumps(content,ensure_ascii=False)+"\n")
def main(i):
url="http://www.maoyan.com/board/4?offset="+str(i)
html=get_page_source(url)
#print(type(html))
for i in pares_page_source(html):
write_to_txt(i)
print(i)
if __name__ == '__main__':
for i in range(10):
main(i*10)