def parsed_html(url):
# 接收一个网址
# 返回解析出的
# 1，电影名 <span class="title">这个杀手不太冷</span>
# 2，分数 <span class="rating_num" property="v:average">9.4</span>
# 3，评价人数 <span>994476人评价</span>
# 4，介绍 <span class="inq">怪蜀黍和小萝莉不得不说的故事。</span>
# 标签找到元素
url = 'http://movie.douban.com/top250'
status_code, headers, body = get(url)
movies_labels = ['<span class="title">', '</span>']
sorces_labels = [
'<span class="rating_num" property="v:average">', '</span>'
]
coments_labels = ['<span>', '人评价</span>']
inqs_labels = ['<span class="inq">', '</span>']
movies = find_element_by_label(body, movies_labels[0], movies_labels[1])
sorces = find_element_by_label(body, sorces_labels[0], sorces_labels[1])
coments = find_element_by_label(body, coments_labels[0], coments_labels[1])
inqs = find_element_by_label(body, inqs_labels[0], inqs_labels[1])
# log("inqs_labels[0]", inqs_labels[0], inqs_labels[1])
# log("m s c i", inqs)
result = [len(movies)]
log("len", len(movies), len(sorces), len(coments), len(inqs))
for i in range(len(movies)):
m = movies[i]
s = sorces[i]
c = coments[i]
i = inqs[i]
op = '\n'
result = m + op + s + op + c + op + i + op
log("result\n", result)
return movies, sorces, coments, inqs
def test_find_between():
url = 'http://movie.douban.com/top250'
status_code, headers, body = get(url)
content = body
left = '<span class="title">'
right = '</span>'
left1 = '<span class="rating_num" property="v:average">'
# print("contens", content )
content1 = find_between(content, left, right)
content2 = find_between(content, left1, right)
print('结果1 ', content1)
def parsed_html(url):
# 接收一个网址
# 返回解析出的
# 1，电影名 <span class="title">这个杀手不太冷</span>
# 2，分数 <span class="rating_num" property="v:average">9.4</span>
# 3，评价人数 <span>994476人评价</span>
# 4，<span class="inq">怪蜀黍和小萝莉不得不说的故事。</span>
# 标签找到元素
url = 'http://movie.douban.com/top250'
status_code, headers, body = get(url)
movies = find_element_by_label(body, l, r)
def test_find_element_by_label():
url = 'http://movie.douban.com/top250'
status_code, headers, body = get(url)
test_items = [
# ('<a href="https://www.douban.com/doubanapp/app?channel=qipao" class="tip-link">豆瓣 5.0 全新发布</a>', ("</a>")),
('<span class="title">', ('</span>')),
# ('<span class="title">肖申克的救赎', ("</span>")),
]
# test_function = find_element_by_label
# left = now_str.find(left_label) + len(left_label)
# right = now_str.find(right_label)
# test_function_name = test_function.__name__
for t in test_items:
log("t", t)
left_label, right_label = t
find_element_by_label(body, left_label, right_label)
def test_find_element_by_label():
# left = '<span class="title">'
left = '<a href="https://www.douban.com/group" target="_blank" data-moreurl-dict="{"from":"top-nav-click-group","uid":"0"}">'
right = '</span>'
url = 'http://movie.douban.com/top250'
status_code, headers, body = get(url)
test_items = [
# ('<a href="https://www.douban.com/doubanapp/app?channel=qipao" class="tip-link">豆瓣 5.0 全新发布</a>', ("</a>")),
('<span class="title">', ('</span>')),
# ('<span class="title">肖申克的救赎', ("</span>")),
]
# test_function = find_element_by_label
# left = now_str.find(left_label) + len(left_label)
# right = now_str.find(right_label)
# test_function_name = test_function.__name__
for t in test_items:
log("t", t)
left_label, right_label = t
find_element_by_label(body, left_label, right_label)
# 作业 2.6
#
"""
通过在浏览器页面中访问 豆瓣电影 top250 可以发现
1, 每页 25 个条目
2, 下一页的 URL 如下
https://movie.douban.com/top250?start=25
因此可以用循环爬出豆瓣 top250 的所有网页
于是就有了豆瓣电影 top250 的所有网页
由于这 10 个页面都是一样的结构，所以我们只要能解析其中一个页面就能循环得到所有信息
所以现在的程序就只剩下了解析 HTML
请观察规律，解析出
1，电影名
2，分数
3，评价人数
4，引用语（比如第一部肖申克的救赎中的「希望让人自由。」）
解析方式可以用任意手段，如果你没有想法，用字符串查找匹配比较好(find 特征字符串加切片)
"""
if __name__ == '__main__':
# test_path_with_query()
# test_header_from_dict()
dic = get('https://movie.douban.com/top250')
# log('body', dic[-1])
parse_body(dic[-1])