python返回字符串false_Python的startswith方法放进去的列表内容明明有我输入的字符串却返回false有哪些原因？...

from lxml import etree

import requests

BASE_DOMIN="http://www.ygdy8.net"

headers={

"User-Agent":"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Mobile Safari/537.36"

}

url="http://www.ygdy8.net/html/gndy/dyzz/list_23_{}.html".format(1)

def get_detail_url(url):

re = requests.get(url, headers=headers)

text = re.text

# requests会用自己默认的编码方式解码，电影天堂的解码方式错误所以会产生乱码

# parser=etree.HTMLParser(encoding="utf-8")

html = etree.HTML(text)

dianyin_link = html.xpath("//table[@class='tbspan']//a/@href")

#name = html.xpath("//table[@class='tbspan']//tr//a/text()")[0]

#content = html.xpath("//table[@class='tbspan']//tr/td[@colspan='2']/text()")[0]

dianyin_link=list(map(lambda url:BASE_DOMIN+url,dianyin_link))

return dianyin_link

def parse_replace(text1,rule):

text = text1.replace(rule, "").strip()

return text

def parse_detail_url(url):

movie={}

respones=requests.get(url,headers=headers)

texts=respones.content.decode('gbk')

html=etree.HTML(texts)

detail_name=html.xpath("//font[@color='#07519a']/text()")[0]

movie['title']=detail_name

#电影名字

detail_infro=html.xpath("//div[@id='Zoom']")[0]

#电影详情

detail_img=detail_infro.xpath(".//img/@src")

cover=detail_img[0]

#电影海报

screen_shot=detail_img[1]

#电影截图

movie["cover"]=cover

movie["screeshot"]=screen_shot

detail_text=html.xpath("//div[@id='Zoom']//text()")

print(detail_text)

for index,text in enumerate(detail_text):

#为什么这里一直是false!!!明明有年代这个字符串

print(text.startswith("◎年　　代"))

if text.startswith("◎年　　代"):

text = parse_replace(text,"◎年　　代")

movie["年份"]=text

elif text.startswith("◎产　　地"):

text = parse_replace(text,"◎产　　地")

movie["产地"]=text

print(text)

elif text.startswith("◎类　　别"):

text = parse_replace(text, "◎类　　别")

movie["类别"]=text

elif text.startswith("◎主　　演"):

text = parse_replace(text, "◎主　　演")

actors=[text]

for x in range(index+1,len(detail_text)):

actor1=detail_text[x].strip()

if actor1.startswith("◎"):

break

actors.append(actor1)

movie["actor"]=actors

elif text.startswith("◎简　　介"):

text=parse_replace(text,"◎简　　介")

for x in range(index+1,len(detail_text)):

profile=detail_text[x].strip()

if profile.startswith("【下载地址】"):

break

movie["profile"]=profile

download_url=html.xpath("//td[@bgcolor='#fdfddf']/a/@href")[0]

movie["下载地址"]=download_url

return movie

def spiders():

base_url="http://www.ygdy8.net/html/gndy/dyzz/list_23_{}.html"

for i in range(1,3):

url=base_url.format(i)

movies=[]

#print(url)

detail_urls=get_detail_url(url)

for detail_url in detail_urls:

movie=parse_detail_url(detail_url)

movies.append(movie)

print("$"*20)

print(movies)

if __name__=="__main__":

spiders()