def get_fund_mapping(self):
# sub_code, sub_name, main_code, main_name
sub_to_main_mapping = []
html = requests.get(self._url, timeout=30.0).content
document = PyQuery(unicode(html, 'utf-8'))
fund_blocks = [document.items('.aa'), document.items('.dd')]
for each_block in fund_blocks:
for class_tag in each_block:
items_list = [item.text() for item in class_tag.items('td')]
sub_to_main_mapping.append((items_list[1], items_list[3]))
return dict(sub_to_main_mapping)
def find_indicacoes(html: str) -> List[Indicacao]:
d = PyQuery(html)
indicacoes = []
current_index = 0
for heading in d.items('div[class="w3-col w3-left-align"] > p > b'):
indicacoes.append(dict({
"heading": heading.text(),
}))
for content in d.items('div#Demo1'):
autor = content('div[class="w3-col w3-left w3-twothird"]').remove(
'label').remove('br').text()
protocolo = content('div[class="w3-col w3-left w3-third"]').remove(
'label').remove('br').text()
tramites = []
tramite_idx = 0
for content_row in content.items('div[class="w3-row-padding"]'):
for col in content_row.items(
'div[class="w3-col w3-left w3-quarter"]'):
text = col.text()
if text not in [
'Data de Trâmite', 'Hora de Trâmite', 'Trâmite',
'Anotações'
]:
if tramite_idx == 0:
tramites.append([text])
else:
tramites[-1].append(text)
tramite_idx += 1
if tramite_idx == 4:
tramite_idx = 0
indicacoes[current_index] = {
**indicacoes[current_index],
"autor":
autor,
"protocolo":
protocolo,
"tramites": [{
"data": tramite[0],
"hora": tramite[1],
"texto": tramite[2],
"anotacoes": tramite[3]
} for tramite in tramites],
}
current_index += 1
return indicacoes
def __init__(self, data: PyQuery, pages: List[PyQuery], index: int):
self.origin: PyQuery = data # 原始数据
# 结果返回值
self.raw: List[GoogleItem] = [GoogleItem(i) for i in data.items()]
self.index: int = index # 当前页
self.page: int = len(pages) # 总页数
self.pages: List[PyQuery] = pages # 页面源
def getResTb():
html = fileworker.getHTML()
pq = PyQuery(html)
result = dict()
blocks = list()
for i in pq.items('.row.result'):
list.append(i)
def Parse(self, html_data):
parser_result = ParserResult()
product_list = parser_result.product_list
doc = PyQuery(html_data)
for productEl in doc.items(self._item_query):
link_el = productEl.find(self._link_el_query)
if not link_el:
logging.info('Failed to find link element!')
continue
url = _GetLinkHref(link_el[0])
if not url:
logging.info('Failed to find href!')
continue
name_el = productEl.find(self._name_el_query)
if not name_el:
logging.info('Failed to find name element!')
continue
name = _GetText(name_el[0])
image_el = productEl.find(self._image_el_query)
if not image_el:
logging.info('Failed to find image element!')
continue
image_url = _GetImageSrc(image_el[0])
if not image_url:
logging.info('Failed to find image src!')
continue
product = product_list.product.add()
product.url = url.strip()
product.name = name
product.image_url = image_url.strip()
return parser_result
def extract_urls(html): #提取url是cpu操作，无需改成协程
'''文章解析出url放入seen_urls队列'''
pq = PyQuery(html)
for link in pq.items("a"):
url = link.attr("href") #去掉已经爬取过的url，放入到等待爬取的列表
if url and url.startswith("http") and url not in seen_urls:
waitting_urls.put_nowait(url)
def FetchAndSave():
#百度风云榜页面网址(含有50个热门新闻的关键词)
fengyunbang_url = 'http://top.baidu.com/buzz?b=1'
resp = requests.get(fengyunbang_url)
resp.encoding='gb2312'
#新建excel文件保存数据。
csvf = open('data.csv', 'a+', encoding='gbk', newline='')
writer = csv.writer(csvf)
writer.writerow(('news_content', 'keyword'))
#从heml文件中解析出 事件字段和 网址字段
doc = PyQuery(resp.text)
for item in doc.items('.keyword'):
keyword = item('a').text().split(' ')[0]
keyword_link = item('a').attr.href
news_links = get_keywords_news_links(keyword_link)
for news_link in news_links:
try:
content = get_news_content(news_link)
if content:
print(keyword, content[0:20])
writer.writerow((content, keyword))
except:
print(news_link)
def getResTb():
html = fileworker.getHTML()
pq = PyQuery(html)
result = dict()
blocks = list()
for i in pq.items('.row.result'):
list.append(i)
def all_sub_div(partial):
"""Helper function that returns all the direct sub div of the given partial.
Params:
partial (str): an HTML partial to analyse it must be a div element.
Returns:
list(str): List of the content of all the direct `div` child elements
in the partial.
Empty list if the root element is not a div or if not direct div child exist.
Examples:
>>> all_sub_div('<div></div>')
[]
>>> all_sub_div('<section></section>')
[]
>>> all_sub_div('<div><div>toto</div><div>titi</div></div>')
['<div>toto</div>', '<div>titi</div>']
>>> all_sub_div('<div><div>toto</div></div>')
['<div>toto</div>']
>>> all_sub_div('<section><div>toto</div></section>')
[]
"""
d = PyQuery(partial)
if not d(":root").is_("div"):
return []
return [elem.outer_html() for elem in d.items(":root>div")]
def extract_urls(html):
"""从返回的html中及解析出新的url"""
pq = PyQuery(html)
for link in pq.items("a"):
url = link.attr("href")
if url and url.startswith("http") and url not in seen_urls:
waitting_urls.append(url)
def get_organization():
url = 'https://summerofcode.withgoogle.com/archive/2017/organizations/'
response = open_url(url)
soup = PyQuery(response)
soup = soup('.organization-card__link')
for each in soup.items():
yield 'https://summerofcode.withgoogle.com' + each.attr('href')
def video_download(url,title):
response = requests.get(url,headers=headers).text
doc = PyQuery(response)
#<div class="RichText ztext Post-RichText __reader_view_article_wrap_786807993615199__"><p>知乎里我添加了一个新专栏，是关于硬笔行书的。</p><p><br>行书是介于楷书与草书之间的一种书体，它不像草书那样潦草，也不像楷书那样规矩板正。它就好比正在行走的人，既有动感，速度也不会很快。草书虽然潇洒，楷书虽然俊美，但都不利于日常书写与交流。行走的汉字才是最适合在日常生活中书写的。</p><p><br>这个系列每期会写一个单字，有单字静图、动图还有书写视频。</p><p><br>对本人硬笔行书感兴趣的书友可以关注。有问题的也欢迎在评论区与我交流。我也会加倍勤奋争取把这个系列做到日更，争取让更多硬笔爱好者每天都能学到新字。</p><hr><p><b>这是本系列第 192 次更新。</b></p><div><div class="RichText-video" data-za-detail-view-path-module="VideoItem" data-za-extra-module="{"card":{"content":{"type":"Video","sub_type":"SelfHosted","video_id":"1161414208179904512","is_playable":true}}}"><div class="VideoCard VideoCard--interactive"><div class="VideoCard-layout"><div class="VideoCard-video"><div class="VideoCard-video-content"><div class="VideoCard-player"><iframe frameborder="0" allowfullscreen="" src="https://www.zhihu.com/video/1161414208179904512?autoplay=false&useMSE="></iframe></div></div></div><div class="VideoCard-content"><div class="VideoCard-title">硬笔行书每日一字 · 可</div></div></div><div class="VideoCard-mask"></div></div></div></div><figure data-size="normal"><noscript><img src="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_b.jpg" data-caption="" data-size="normal" data-rawwidth="2110" data-rawheight="2110" class="origin_image zh-lightbox-thumb" width="2110" data-original="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_r.jpg"/></noscript><img src="https://pic3.zhimg.com/80/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_hd.jpg" data-caption="" data-size="normal" data-rawwidth="2110" data-rawheight="2110" class="origin_image zh-lightbox-thumb lazy" width="2110" data-original="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_r.jpg" data-actualsrc="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_b.jpg" data-lazy-status="ok"></figure><figure data-size="normal"><noscript><img src="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.gif" data-caption="" data-size="normal" data-rawwidth="400" data-rawheight="400" data-thumbnail="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" class="content_image" width="400"/></noscript><div class="RichText-gifPlaceholder"><div class="GifPlayer" data-size="normal" data-za-detail-view-path-module="GifItem"><img class="ztext-gif" role="presentation" src="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" data-thumbnail="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" data-size="normal"><svg width="60" height="60" viewBox="0 0 60 60" class="GifPlayer-icon"><g fill="none" fill-rule="evenodd"><ellipse fill="#000" opacity="0.45" cx="30" cy="30" rx="30" ry="30"></ellipse><ellipse stroke="#FFF" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4,1,4" cx="30" cy="30" rx="26" ry="26"></ellipse><svg x="16" y="18.5" class="GifPlayer-icon"><path d="M12.842 12.981V11.4H7.64v1.653h3.27v.272c-.018 1.881-1.442 3.147-3.516 3.147-2.382 0-3.876-1.846-3.876-4.834 0-2.936 1.485-4.79 3.832-4.79 1.732 0 2.936.835 3.428 2.364h1.977c-.43-2.566-2.522-4.201-5.405-4.201-3.55 0-5.845 2.601-5.845 6.644 0 4.096 2.268 6.654 5.863 6.654 3.322 0 5.475-2.083 5.475-5.327zM17.518 18V5.317H15.55V18h1.97zm5.142 0v-5.256h5.449v-1.74h-5.45V7.11h5.95V5.317h-7.918V18h1.969z" fill="#fff"></path></svg></g></svg></div></div></figure><p></p></div>V<div class="RichText ztext Post-RichText __reader_view_article_wrap_786807993615199__"><p>知乎里我添加了一个新专栏，是关于硬笔行书的。</p><p><br>行书是介于楷书与草书之间的一种书体，它不像草书那样潦草，也不像楷书那样规矩板正。它就好比正在行走的人，既有动感，速度也不会很快。草书虽然潇洒，楷书虽然俊美，但都不利于日常书写与交流。行走的汉字才是最适合在日常生活中书写的。</p><p><br>这个系列每期会写一个单字，有单字静图、动图还有书写视频。</p><p><br>对本人硬笔行书感兴趣的书友可以关注。有问题的也欢迎在评论区与我交流。我也会加倍勤奋争取把这个系列做到日更，争取让更多硬笔爱好者每天都能学到新字。</p><hr><p><b>这是本系列第 192 次更新。</b></p><div><div class="RichText-video" data-za-detail-view-path-module="VideoItem" data-za-extra-module="{"card":{"content":{"type":"Video","sub_type":"SelfHosted","video_id":"1161414208179904512","is_playable":true}}}"><div class="VideoCard VideoCard--interactive"><div class="VideoCard-layout"><div class="VideoCard-video"><div class="VideoCard-video-content"><div class="VideoCard-player"><iframe frameborder="0" allowfullscreen="" src="https://www.zhihu.com/video/1161414208179904512?autoplay=false&useMSE="></iframe></div></div></div><div class="VideoCard-content"><div class="VideoCard-title">硬笔行书每日一字 · 可</div></div></div><div class="VideoCard-mask"></div></div></div></div><figure data-size="normal"><noscript><img src="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_b.jpg" data-caption="" data-size="normal" data-rawwidth="2110" data-rawheight="2110" class="origin_image zh-lightbox-thumb" width="2110" data-original="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_r.jpg"/></noscript><img src="https://pic3.zhimg.com/80/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_hd.jpg" data-caption="" data-size="normal" data-rawwidth="2110" data-rawheight="2110" class="origin_image zh-lightbox-thumb lazy" width="2110" data-original="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_r.jpg" data-actualsrc="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_b.jpg" data-lazy-status="ok"></figure><figure data-size="normal"><noscript><img src="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.gif" data-caption="" data-size="normal" data-rawwidth="400" data-rawheight="400" data-thumbnail="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" class="content_image" width="400"/></noscript><div class="RichText-gifPlaceholder"><div class="GifPlayer" data-size="normal" data-za-detail-view-path-module="GifItem"><img class="ztext-gif" role="presentation" src="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" data-thumbnail="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" data-size="normal"><svg width="60" height="60" viewBox="0 0 60 60" class="GifPlayer-icon"><g fill="none" fill-rule="evenodd"><ellipse fill="#000" opacity="0.45" cx="30" cy="30" rx="30" ry="30"></ellipse><ellipse stroke="#FFF" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4,1,4" cx="30" cy="30" rx="26" ry="26"></ellipse><svg x="16" y="18.5" class="GifPlayer-icon"><path d="M12.842 12.981V11.4H7.64v1.653h3.27v.272c-.018 1.881-1.442 3.147-3.516 3.147-2.382 0-3.876-1.846-3.876-4.834 0-2.936 1.485-4.79 3.832-4.79 1.732 0 2.936.835 3.428 2.364h1.977c-.43-2.566-2.522-4.201-5.405-4.201-3.55 0-5.845 2.601-5.845 6.644 0 4.096 2.268 6.654 5.863 6.654 3.322 0 5.475-2.083 5.475-5.327zM17.518 18V5.317H15.55V18h1.97zm5.142 0v-5.256h5.449v-1.74h-5.45V7.11h5.95V5.317h-7.918V18h1.969z" fill="#fff"></path></svg></g></svg></div></div></figure><p></p></div>
#<div class="Post-RichTextContainer"><div class="RichText ztext Post-RichText __reader_view_article_wrap_786807993615199__"><p>知乎里我添加了一个新专栏，是关于硬笔行书的。</p><p><br>行书是介于楷书与草书之间的一种书体，它不像草书那样潦草，也不像楷书那样规矩板正。它就好比正在行走的人，既有动感，速度也不会很快。草书虽然潇洒，楷书虽然俊美，但都不利于日常书写与交流。行走的汉字才是最适合在日常生活中书写的。</p><p><br>这个系列每期会写一个单字，有单字静图、动图还有书写视频。</p><p><br>对本人硬笔行书感兴趣的书友可以关注。有问题的也欢迎在评论区与我交流。我也会加倍勤奋争取把这个系列做到日更，争取让更多硬笔爱好者每天都能学到新字。</p><hr><p><b>这是本系列第 192 次更新。</b></p><div><div class="RichText-video" data-za-detail-view-path-module="VideoItem" data-za-extra-module="{"card":{"content":{"type":"Video","sub_type":"SelfHosted","video_id":"1161414208179904512","is_playable":true}}}"><div class="VideoCard VideoCard--interactive"><div class="VideoCard-layout"><div class="VideoCard-video"><div class="VideoCard-video-content"><div class="VideoCard-player"><iframe frameborder="0" allowfullscreen="" src="https://www.zhihu.com/video/1161414208179904512?autoplay=false&useMSE="></iframe></div></div></div><div class="VideoCard-content"><div class="VideoCard-title">硬笔行书每日一字 · 可</div></div></div><div class="VideoCard-mask"></div></div></div></div><figure data-size="normal"><noscript><img src="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_b.jpg" data-caption="" data-size="normal" data-rawwidth="2110" data-rawheight="2110" class="origin_image zh-lightbox-thumb" width="2110" data-original="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_r.jpg"/></noscript><img src="https://pic3.zhimg.com/80/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_hd.jpg" data-caption="" data-size="normal" data-rawwidth="2110" data-rawheight="2110" class="origin_image zh-lightbox-thumb lazy" width="2110" data-original="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_r.jpg" data-actualsrc="https://pic3.zhimg.com/v2-0b5f6fb5b9905f4e89a3081b9c5c4ade_b.jpg" data-lazy-status="ok"></figure><figure data-size="normal"><noscript><img src="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.gif" data-caption="" data-size="normal" data-rawwidth="400" data-rawheight="400" data-thumbnail="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" class="content_image" width="400"/></noscript><div class="RichText-gifPlaceholder"><div class="GifPlayer" data-size="normal" data-za-detail-view-path-module="GifItem"><img class="ztext-gif" role="presentation" src="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" data-thumbnail="https://pic2.zhimg.com/v2-4c94b4f2c6ddadaecead094ee1042b09_b.jpg" data-size="normal"><svg width="60" height="60" viewBox="0 0 60 60" class="GifPlayer-icon"><g fill="none" fill-rule="evenodd"><ellipse fill="#000" opacity="0.45" cx="30" cy="30" rx="30" ry="30"></ellipse><ellipse stroke="#FFF" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4,1,4" cx="30" cy="30" rx="26" ry="26"></ellipse><svg x="16" y="18.5" class="GifPlayer-icon"><path d="M12.842 12.981V11.4H7.64v1.653h3.27v.272c-.018 1.881-1.442 3.147-3.516 3.147-2.382 0-3.876-1.846-3.876-4.834 0-2.936 1.485-4.79 3.832-4.79 1.732 0 2.936.835 3.428 2.364h1.977c-.43-2.566-2.522-4.201-5.405-4.201-3.55 0-5.845 2.601-5.845 6.644 0 4.096 2.268 6.654 5.863 6.654 3.322 0 5.475-2.083 5.475-5.327zM17.518 18V5.317H15.55V18h1.97zm5.142 0v-5.256h5.449v-1.74h-5.45V7.11h5.95V5.317h-7.918V18h1.969z" fill="#fff"></path></svg></g></svg></div></div></figure><p></p></div></div>
for item in doc.items('#root .Post-RichTextContainer div'):
#<span class="z-ico-video"/>https://www.zhihu.com/video/1161414208179904512</span></span>
#for url in item.items('.z-ico-video '):
#<span class="z-ico-video"/>**************27****28******和等于55
videourl = str(item.find('a span .z-ico-video'))[55:]
#print(videourl)
#获取视频链接的存储json文件链接
videos = 'https://lens.zhihu.com/api/v4/videos/'+videourl
resp = requests.get(videos,headers=headers).text
urls = json.loads(resp)
#获取视频链接
videourl = urls['playlist']['LD']['play_url']
print(videourl)
videourl = videourl.replace('&','&').replace(' ','')
#下载视频
videofile = requests.get(videourl,headers=headers)
with open(title+'.mp4','wb') as file:
file.write(videofile.content)
print('完成下载：'+title+'.mp4')
time.sleep(1)
def gain_data():
"""
:return:
"""
for i in range(1, PAGE_NUM + 1):
time.sleep(random.randint(5, 9))
url = "https://jobs.51job.com/pachongkaifa/p" + str(i)
r = requests.get(url, headers=headers)
r.encoding = "gbk"
content = PyQuery(r.text)(".detlist.gbox").children("div")
for d in content.items():
info = d(".info span").text().split(" ")
data["Job"].append(d(".info .title").text())
data["Company"].append(d(".info a").text().split(" ")[-1])
data["Location"].append(info[-3])
data["Salary"].append(info[-2])
data["Date"].append(info[-1])
order = d(".order").text().split("|")
data["Education"].append(list_helper(order[0]))
data["Experience"].append(list_helper(order[1]))
data["Type"].append(list_helper(order[2]))
data["Scope"].append(list_helper(order[3]))
data["Detail"].append(d(".text").text().replace(" ", "", -1))
data["Url"].append(d(".info span a").attr("href"))
pandas.DataFrame(data).to_csv("../resource/qcwy/data.csv")
def extract_urls(html):
# urls = []
doc = PyQuery(html)
for link in doc.items("a"): # 获取a标签
url = link.attr("href") # a标签中的href属性
if url and url.startswith("https") and url not in seen_urls:
# urls.append(url) # 如果详情页还有url(初始页时有)，可以将url加入到urls中，然后迭代爬取
waitting_urls.append(url) # 待爬取的url加到waitting队列中
def extract_urls(html):
urls = []
pq = PyQuery(html)
for link in pq.items("a"):
url = link.attr("href")
if url and url.startswith('http') and url not in seen_urls:
urls.append(url)
waiting_urls.append(url)
def get_technologies(url):
l = []
response = open_url(url)
soup = PyQuery(response)
soup = soup('.organization__tag')
for each in soup.items():
l.append(each.text())
return l
def get_ingredients():
pages = send_requests()
ingredients = []
for page in pages:
pq = PyQuery(page)(".grid-view")
ig = [i.attr("id") for i in pq.items("li")]
ig = [i.replace("_", " ") for i in ig]
ingredients.extend(ig)
return ingredients
def extract_urls(html):
urls = []
pq = PyQuery(html)
for link in pq.items("a"):
url = link.attr("href")
if url and url.startswith("http") and url not in seen_urls:
urls.append(url)
waitting_urls.append(url)
return urls
def get_flight_ids(html_text):
__pq = PyQuery(html_text).find("tbody").find("td.inputselect").find(
"div.content").find("input")
ids = []
for __node in __pq.items():
if (__node.hasClass("radio-ajax")):
__matched = regex("[A-Z]{2}.*[A-Z]", str(__node.attr("value")))
ids.extend(__matched)
return ids
def get_movies(self, html):
doc = PyQuery(html)
for item in doc.items('.board-item-content'):
return {
'name': item.find('.name').text(),
'stars': item.find('.star').text().split('：')[1],
'time': item.find('.releasetime').text().split('：')[1],
'score': item.find('.score').text()
}
def extract_urls(html):
urls = []
pq = PyQuery(html)
for link in pq.items('a'):
url = link.attr("href")
if url and url.startwith("http") and url not in seen_urls:
urls.append(url)
waitting_urls.append(url)
return urls
def extract_urls(html): # html中提取所有url
urls = []
pq = PyQuery(html)
for link in pq.items('a'):
url = link.attr('href')
if url and url.startwith('http') and url not in seen_urls:
urls.append(url)
waitting_urls.append(urls)
return urls
def decode_html(html_text):
'''解析网页的电影数据'''
doc = PyQuery(html_text)
for item in doc.items('.board-wrapper dd'):
yield {
'name': item.find('.name').text(),
'actors': item.find('.star').text(),
'time': item.find('.releasetime').text(),
'score': item.find('.score').text()
}
def extrack_urls(html):
urls = []
if html:
pq = PyQuery(html)
for link in pq.items('a'):
url = link.attr('href')
# 判断url,踢出不符合条件的url
if url and url.startswith('http') and url not in seen_urls:
urls.append(url)
waitting_urls.append(url)
return urls
def extract_url(html):
urls = []
pq = PyQuery(html)
# 爬取所有a链接
for link in pq.items("a"):
# 提取href属性
url = link.attr('href')
if url and url.startswith('http') and url not in seen_urls: # 判断是否重复或是否是http
urls.append(url)
waitting_url.append(url)
return urls
def extract_urls(html):
print("extract_html", html)
urls = []
pq = PyQuery(html)
for link in pq.items("a"):
url = link.attr("href")
if url and url.startswith("http") and url not in seen_urls:
urls.append(url)
waitting_urls.append(url)
print(waitting_urls)
return urls
async def main():
loop = asyncio.get_running_loop()
async with aiohttp.ClientSession() as session:
html = await fetch(session, "http://www.biquge.cm/12/12097/")
pq = PyQuery(html)
for item in pq.items("dd a"):
title = item.text()
text = await get_text(session, item.attr("href"))
# 兼容阻塞旧代码
await loop.run_in_executor(None, save, title, text)
async def extract_urls(html):
urls = []
pq = PyQuery(html)
# 取所有的url
for link in pq.items('a'):
url = link.attr('href')
# 过滤重复的url
if url and url.startswith('http') not in seen_urls:
urls.append(url)
waitting_urls.append(url)
return urls
def getItemsByKeyword(
keyword,
encoding='GBK',
page=1,
price=None,
):
if not PyQuery:
return []
items = []
domain = \
'http://s.taobao.com/search?q=$Q$&style=list&bcoffset=1&tab=all&cd=false&v=auction&sort=sale-desc&s={0}'
domain = domain.replace('$Q$',
repr(keyword.decode(encoding).
encode('GBK')).
replace('\\x', '%').upper()[1:-1])
domain = domain.replace(' ', '%20')
# price interval
if price:
domain = domain \
+ '&filter=reserve_price%5B{0}%2C{1}%5D'.format(price[0], price[1])
# price interval end
for i in range(page):
url = domain.format(i * 40)
r = __import__('requests').get(url)
encoding = r.encoding
py = PyQuery(r.content.decode(encoding))
page_num = 0
for i, meta_item in enumerate(py.items("div[nid]")):
page_num += 1
try:
info = {
'rank': i + 1,
'keyword': keyword,
'itemName': meta_item('h3 a').attr('title').encode('utf-8'),
'itemId': meta_item.attr('nid'),
'itemPic': meta_item('img').attr('src'),
'wangwang': meta_item('.seller a').html().encode('utf-8').strip(),
'userNumId': re.findall(r'id\=(\d+)', meta_item('.seller a').attr('href'))[0],
'price': re.findall(r'\d+\.\d*', meta_item('.price').html().encode('utf-8'))[0],
'location': (meta_item('.loc div').html() or '').encode('utf-8'),
'tradeNum': re.findall(r'\d+', meta_item('.dealing div').html() or '0')[-1],
'rateNum': re.findall(r'\d+', (meta_item('.count a').html() or '0').encode('utf-8'))[0],
}
items.append(info)
except:
traceback.print_exc()
# continue
# if page_num < 40:
# break
return items
def _get_other_urls(self, data: PyQuery) -> None:
for link in data.items():
if link.attr("href") == "#":
continue
if link.text() == "SauceNao":
self.saucenao_url = "https:" + link.attr("href")
elif link.text() == "ascii2d.net":
self.ascii2d_url = link.attr("href")
elif link.text() == "Google Images":
self.google_url = "https:" + link.attr("href")
elif link.text() == "TinEye":
self.tineye_url = "https:" + link.attr("href")
def extract_links(source):
'''
提取出详情页的链接
'''
pq = PyQuery(source)
for link in pq.items("a"):
_url = link.attr("href")
if _url and re.match('https://.*?/\d+.html', _url) and _url.find(
'{}.lianjia.com'.format(city)):
links_detail.add(_url)
print(links_detail)
def decode_html(html_text):
# print(html_text)
doc = PyQuery(html_text)
# print(doc)
for item in doc.items('.board-wrapper dd'):
# print(item)
yield {
'name': item.find('.name').text(),
'actors': item.find('.star').text(),
'time': item.find('.releasetime').text(),
'score': item.find('.score').text(),
}
def get_contributive_info(self, session, text, i_d, data):
# 获得页码信息
total_page_num = self.get_page_num(text, '#paging') + 1
if total_page_num == 1:
total_page_num += 1
for page in xrange(1, total_page_num):
try:
url = 'http://{host}/business/QueryInvList.jspx?pno={page}&order=0&mainId={i_d}'.format(
host=self.host, page=page, i_d=i_d)
r = self.filter_request(session, session.get, url)
if r is None:
self.append_model(data,
Model.contributive_info,
url,
'',
status=self.STATUS_FAIL)
continue
self.append_model(data, Model.contributive_info, url, r.text)
index = 0
tr_list = PyQuery(
r.text, parser='html').find('.detailsListGDCZ').find('tr')
item_list = tr_list.items()
for item in item_list:
index += 1
onclick = item.find('a').attr('onclick')
if onclick is None or onclick == '':
continue
invest_list = self.invest_search_obj.findall(
onclick.encode('utf-8'))
for invest_id in invest_list:
url = 'http://{host}/queryInvDetailAction.jspx?invId={i_d}'.format(
host=self.host, i_d=invest_id)
r = self.filter_request(session, session.get, url)
if r is None:
self.append_model(data,
Model.contributive_info,
url,
'',
status=self.STATUS_FAIL,
classify=Model.type_detail)
continue
self.append_model(data,
Model.contributive_info,
url,
r.text,
classify=Model.type_detail)
except Exception as e:
self.log.exception(e)
def unpack_events(html, args):
query = PyQuery(html)
logger.debug("Source encoding: {} ".format(query.encoding))
rows = query.items('tr')
offset = 0
events = []
for row in rows:
parsed_row = __parse_row(row)
event_id = offset
events.append(parsed_row)
offset += 1
logger.debug("Parsed {} entries".format(offset))
return events
def process_html_file(fi):
f = open(fi,'r')
d = PyQuery(f.read())
f.close()
year = None
links = {}
for a in d.items('.toc a'):
if len(a.text()) == 4:
year = a.text()
links[year] = []
else:
if year:
links[year].append( (a.attr('href'), a.text()) )
else:
if 'NONE' not in links:
links['NONE'] = []
links['NONE'].append( (a.attr('href'), a.text()) )
logger.debug('Retrieved data %s %s' % (a.text(), a.attr('href')))
data = []
for year in links.keys():
for link_id, link_name in links[year]:
logger.info('Getting text at %s' % link_id)
title = date = text = ''
for x in d(link_id).parents('p').nextAll().items():
logger.debug('X: %s' % x.outerHtml())
if '<a' in x.outerHtml():
break
elif 'End of the Project Gutenberg' in x.text():
break
elif '<h2' in x.outerHtml():
title = x.text()
elif '<h3' in x.outerHtml():
date = x.text()
elif '<p' in x.outerHtml():
text += RE_CLEAN_TEXT.sub(x.text().replace('\n',' ').replace(' ','').replace('\r',' '), ' ')
else:
logger.error('Unrecognized tag: %s' % x.outerHtml())
if 'Gutenberg' in text:
logger.error('%s\n%s' % (title,text))
logger.debug('\nTitle: %s\nDate: %s\nText: %s' % (title, date, text))
data.append((year, date, title, text))
logger.info('Retrieved %d pieces' % len(data))
return data
async def Start():
timestamp = time.time()
parser = argparse.ArgumentParser(description="BioTC by Bioruebe (https://bioruebe.com), 2014-2019, Version 3.0.0, released under a BSD 3-clause style license.\n\nBioTC is a small application to simplify trading Steam Trading Cards with the SteamCardExchange bot by comparing the user's Steam inventory with the available cards on steamcardexchange.net")
parser.add_argument("-n", "--name", action="store", type=str, default=None, help="Use specified Steam ID instead of reading it from " + STEAM_ID_FILE_NAME)
parser.add_argument("-l", "--limit", action="store", type=int, default=-1, help="Stop searching after n sets have been found")
args = parser.parse_args()
parser.print_help()
print("\n-----------------------------------------------------------------------------\n")
if args.name is None:
try:
f = open(STEAM_ID_FILE_NAME)
args.name = f.read()
except:
pass
if args.name is None:
sys.exit("Error: Could not read SteamID from file. Make sure the file '" + STEAM_ID_FILE_NAME + "' contains a valid SteamID.")
result = {
"sets": [],
"steamID": args.name,
"cardsCount": 0,
"gameCount": 0,
"completeSets": 0,
"processingTime": 0,
"time": 0
}
async with aiohttp.ClientSession() as session:
print("Loading Steam inventory")
url = "https://steamcommunity.com/id/" + args.name + "/inventory/json/753/6"
raw_json = await fetch(session, url)
cardData = json.loads(raw_json)
# print(cardData)
if cardData is None or not cardData["success"]:
sys.exit("Invalid JSON data received. Aborting.")
for key, card in cardData["rgDescriptions"].items():
# Ignore emoticons, backgrounds
if "Trading Card" not in card["type"]:
# print(card["name"] + " is not a trading card.")
continue
# print(card)
appid = card["market_fee_app"]
try:
game_cards = card_requests[appid]
game_cards.append(card)
except KeyError:
card_requests[appid] = [card]
i = 0
result["gameCount"] = len(card_requests)
for appid, inventory in card_requests.items():
print("Processing " + appid)
url = "https://www.steamcardexchange.net/index.php?inventorygame-appid-" + appid
resp = await fetch(session, url)
time.sleep(0.5)
dom = PyQuery(resp)
game_name = dom("h2").text()
card_items = dom.items(".inventory-game-card-item")
card_set = Set(appid, game_name)
# print(inventory)
for item in card_items:
card = Card(item.find(".card-name").text().strip())
if card.name == "":
# print("[Warning] Invalid card name: " + card.name)
continue
# available = item.find(".green, .orange")
# if not available:
# continue
stock = filter_card_stock_value(item.find(".card-amount").text())
card.bot_inventory = stock[0]
if len(stock) > 1:
card.bot_inventory_pending = stock[1]
try:
card.price = int("".join(filter(str.isdigit, item.find(".card-price").eq(1).text())))
if card_set.standard_price < 1 and card.bot_inventory > 1:
card_set.standard_price = card.price
except ValueError:
pass
card.trade_url = item.find(".button-blue").attr("href")
card.user_inventory = get_card_amount_in_inventory(cardData, inventory, card.name)
card_set.cards.append(card)
card_set.update_complete_sets()
card_set.calculate_total_cost()
card_set.set_progress_class()
card_set.set_card_classes()
card_set.cards.sort(key=lambda c: (c.user_inventory, 10 - c.bot_inventory))
result["completeSets"] += card_set.complete_sets
if card_set.user_inventory_is_empty():
print("User has " + str(card_set.complete_sets) + " complete sets, but no surplus cards in inventory")
continue
if card_set.bot_inventory_is_empty():
print("Bot has no unowned cards (at normal price) for this set")
continue
print(card_set)
result["sets"].append(card_set)
i += 1
if args.limit > 0 and i >= args.limit:
break
env = Environment(loader=FileSystemLoader("."))
template = env.get_template('template.html')
result["cardCount"] = sum(len(list(filter(lambda c: c.user_inventory < 1, s.cards))) for s in result["sets"])
result["processingTime"] = "{:.1f}".format(time.time() - timestamp)
result["time"] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())
html = template.render(result)
file = open("Cards.html", "w", encoding="utf-8")
file.write(html)
file.close()
os.startfile("Cards.html")
def getItemsByKeyword(
keyword,
encoding='utf-8',
page=1,
price=None,
sort='sale-desc'
):
"""
@params sort: renqi-desc/sale-desc/credit-desc/old_starts/price-asc/price-desc
"""
if not PyQuery:
return []
items = []
params = {
'q': '$Q$',
'style': 'grid',
# 'bcoffset': 1,
'tab': 'all',
# 'cd': 'false',
# 'v': 'auction',
'sort': sort,
's': '{0}',
# 'p4poffset': '4',
# 'bcoffset': '-4',
'btab': 0
}
domain = 'http://s.taobao.com/search?' + \
'&'.join(['%s=%s' % (k, v) for k, v in params.items()])
domain = domain.replace('$Q$',
repr(keyword.decode(encoding).
encode('GBK')).
replace('\\x', '%').upper()[1:-1])
domain = domain.replace(' ', '%20')
# price interval
if price:
domain = domain \
+ '&filter=reserve_price%5B{0}%2C{1}%5D'.format(price[0], price[1])
# price interval end
for i in range(page):
url = domain.format(i * 40)
r = requests.get(url, timeout=5, allow_redirects=True)
# encoding = r.encoding
content = eval(repr(r.content).replace('\\x86"', '"').replace('\\x90"', '"'))
py = PyQuery(content.decode(r.encoding))
page_num = 0
for j, meta_item in enumerate(py.items("div[nid]")):
page_num += 1
try:
info = {
'rank': i * 40 + j + 1,
'keyword': keyword.decode(encoding).encode('utf-8'),
'itemName': meta_item('h3 a').attr('title').encode('utf-8'),
'itemId': meta_item.attr('nid').encode('utf-8'),
'itemPic': meta_item('img').attr('src').encode('utf-8'),
'wangwang': meta_item('.seller a').html().encode('utf-8').strip(),
'userNumId': re.findall(r'id\=(\d+)', meta_item('.seller a').attr('href'))[0].encode('utf-8'),
'price': re.findall(r'\d+\.\d*', meta_item('.price').html().encode('utf-8'))[0],
'location': (meta_item('.loc div').html() or '').encode('utf-8'),
'tradeNum': re.findall(r'\d+', meta_item('.dealing div').html() or '0')[-1].encode('utf-8'),
'rateNum': re.findall(r'\d+', (meta_item('.count a').html() or '0').encode('utf-8'))[0],
}
items.append(info)
except:
traceback.print_exc()
# continue
# if page_num < 40:
# break
return items