def parse_pagination(html) -> Tuple[List, str]:
"""find all job links and next page link in pagination html"""
print("Parse Pagination!")
sel = Selector(text=html)
jobs = sel.css('div.item h3 a::attr(href)').extract()
next_page = sel.css('a[aria-label=Next]::attr(href)').extract_first()
return jobs, next_page
def parse_gallery(html):
title = html.css("a::text").get()
url = html.css("a::attr(href)").get()
slides = []
gallery_html = download(ROOT + url)
gallery_page_document = Selector(text=gallery_html)
for slide_element in gallery_page_document.css(".rsSlideContent"):
slide = slide_element.css("img::attr(src)").get()
slides = slides + [slide]
next_gallery_page_url = gallery_page_document.css(
".gall_next_page > a::attr(href)"
).get()
while next_gallery_page_url is not None:
gallery_html = download(ROOT + url + next_gallery_page_url)
gallery_page_document = Selector(text=gallery_html)
for slide_element in gallery_page_document.css(".rsSlideContent"):
slide = slide_element.css("img::attr(src)").get()
slides = slides + [slide]
next_gallery_page_url = gallery_page_document.css(
".gall_next_page > a::attr(href)"
).get()
slides = [slide for slide in slides if slide is not None]
return (title, url, GalleryContent(slides), None)
def test_check_server():
agent = make_connected_agent()
agent.start(auto_register=False)
port = random.randint(5000, 9999)
agent.web.start(hostname="0.0.0.0", port=port)
# wait for web server to be up
counter = 0
while counter < 4:
if agent.web.server is not None:
break
counter += 1
time.sleep(0.1)
assert agent.web.server is not None
response = requests.get(f"http://localhost:{port}/spade")
sel = Selector(text=response.text)
assert sel.css("title::text").get() == "fake agent"
assert sel.css("img::attr(src)").get() == agent.avatar
assert sel.css("ul.products-list > li").getall() == []
agent.stop()
def weibo_spider(url):
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36'
}
response = requests.get(url=search_url, headers=headers)
#构造css文本
css_text = Selector(text=response.text)
wrap_list = css_text.css('.card')
#搜索结果的第一个
weibo_detail_url = 'https:' + wrap_list[0].css(
'.content .from a[target=_blank]::attr(href)').extract_first()
print('本次搜索排第一的内容页面 --> %s ' % weibo_detail_url)
#评论链接的id获取
comment_id = css_text.css('.card-wrap')[0].css(
'::attr(mid)').extract_first()
print('该内容的comment_id --> %s ' % comment_id)
#用户名
user_name = wrap_list[0].css('.info div a[class=name]::attr(nick-name)'
).extract_first() #a[class=name]
print('发布该内容的用户 --> %s ' % user_name)
#uid
user_uid = wrap_list[0].css(
'.info div a[class=s-btn-c]::attr(uid)').extract_first()
print('该用户的UID --> %s ' % user_uid)
#个人页面
personal_page = wrap_list[0].css(
'.info div a[class=name]::attr(href)').extract_first()
print('该用户的个人页面 --> %s ' % personal_page)
return comment_id
def crawl_detail_page(url, title, news_type):
resp_text = requests.get(url).text
sel = Selector(resp_text)
author = sel.css('#articlewrap > div.article-info > div > a::text').extract_first() or \
sel.css('#articlewrap > div.article-info > div::text').extract_first() or ''
author = author.replace("\n", "").strip()
print(f'保存数据 {news_type} {title} {author} {url} 到 数据库') # 用户自由发挥保存。
def job():
br = mechanize.Browser()
br.set_handle_robots(False)
br.addheaders = [
("user-agent",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"
), ('authority', 'www.skybet.com'), ('method', 'GET'),
('path', '/football/specials/transfer-specials'), ('scheme', 'https'),
('accept',
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
), ('accept-encoding', 'gzip, deflate, br'),
('accept-language', 'en-US,en;q=0.8,zh-CN;q=0.6,zh;q=0.4,zh-TW;q=0.2'),
('cache-control', 'max-age=0'),
('cookie',
'sbgCFcustrandno01=82.2; sbgCAcid01=3EBFE797C814A6A4B6B182391BA5B43B; _ga=GA1.2.200552123.1496285371; betCEsessid01=3q9ad11ench0v48vqd6o2cvnf3; sbgCEsitevisitor=11; sbgCEsiteactiveBet=7b674d7ff7c810a5bad7b5f11999f7fd; sbgCAtrial01=betCOB,BetNGU,betTrial7,bingoappNativeNavBar,vegasappNativeNavBar; beta_site_stick=YmV0YQ==; sbgCEsiteactiveSSO=cc89f90083ecb66e2cfc2c50a43dc22d; config=%7B%22attemptedSSOLogin%22%3Atrue%7D; SSOSESSID=828d661bfc4a76371081e3fe508ef81f; __SBA_POLLTIME=1499223165446|loggedOut|true; SSO_SESS_ID=828d661bfc4a76371081e3fe508ef81f; betSsoAutoLoginAttempted=1499223668675; s_pers=%20s_vnum%3D1501814810661%2526vn%253D1%7C1501814810661%3B%20s_invisit%3Dtrue%7C1499225410331%3B%20s_getNewRepeat%3D1499223610336-Repeat%7C1501815610336%3B; s_sess=%20s_ctq%3D0%3B%20s_cc%3Dtrue%3B%20c%3DundefinedDirect%2520LoadDirect%2520Load%3B%20s.prop69%3Dvisitnumber_1%3B%20s_sq%3D%3B'
), ('upgrade-insecure-requests', '1')
]
br.open(url)
print br.response
s = requests.session()
text = s.get(url, headers=header).text
print text
selector = Selector(text=text)
print len((selector.css('div.mktgrp > * >table')))
print len((selector.css('div.mktgrp > * >h3')))
player_odds_list = []
club_odds = []
def get_authors_list(self, seek_type=1):
"""
Get all authors from http://qsc.zww.cn/. The seek_type is always 1.
"""
for i in range(1, 5): # To-do: this is hardcode list page, currently, there are only 90 pages, but there should be another more intelligent way to get the total page Nos.
req = self.poetry_request(1, i)
content = req.content.decode('gb2312', 'ignore') # Decode in Mandarin
selector = Selector(text = content)
content_in_script = selector.css('script').get()
for line in content_in_script.splitlines():
# Iterate each author list page
if not line.startswith('parent.QTS.filllist'):
# This is html text line doesn't contain values we evaluate.
continue
inner_selector = Selector(text = line)
anchor_lines = inner_selector.css('a').getall()
for anchor in anchor_lines:
# Interate each anchor tag
if re.match(r'.*doseek2\((10,.*,.*)\);.*', anchor): # doseek2(10, .*, .*) stands for a author possessing one/some poetry in this website.
author = re.search(r'(?<=\);">)[^\…]+', anchor).group(0)
seek_type, value, pageno = re.search(r'(?<=onclick="doseek2\()[^\)]+', anchor).group(0).split(',')
desc = self.get_author_info(seek_type, value, 1) # Pageno should always be 1
with scopedsession() as session:
# Add every author to DB because adding a batch of keys may have some primary keys exist in the table,
# and it will trigger rollback w/o adding the non-existing new keys.
session.add(
CiAuthor(
name = author,
desc = desc
)
)
def get_winelab_price(url, result_list=None, need_print=False):
try:
cookies = dict(currentRegion='RU-PRI')
site_page = requests.get(url, cookies=cookies, timeout=3)
# write_to_file(site_page, '/root/pricepinger_v2/winelab.txt')
sel = Selector(site_page.text)
except Exception:
if need_print:
print("Ошибка получения по url " + url)
return None
# print(site_page.status_code)
if site_page.status_code != requests.codes.ok:
return None
# title = sel.css('title::text').extract_first()
# title = sel.css('div.description::text').extract_first() #.capitalize()
title = sel.css('h1::text').extract_first() # .capitalize()
price_purple = format_price(sel.css('span.purple::text').extract_first())
price_yellow = format_price(sel.css('span.yellow::text').extract_first())
price_green = format_price(sel.css('span.green::text').extract_first())
price = max(price_purple, price_yellow, price_green)
date_ts = datetime.datetime.now()
result = [title, float(price), url, 'winelab', date_ts]
if result_list is not None:
result_list.append(result)
if need_print is True:
echo_list_to_sting(result)
return result
def parse_job(html) -> dict:
"""find job details in job listing page"""
sel = Selector(text=html)
# setup some processing helpers
join = lambda css, sep='': sep.join(sel.css(css).extract()).strip()
first = lambda css: sel.css(css).extract_first(' ').strip()
item = {}
item['title'] = sel.css('h2.title::text').extract_first()
item['location'] = join('.job-meta a::text', ', ')
item['job_type'] = join('ul.list-unstyled a::text')
item['posted_date'] = join(
'div#affix-box p:contains("Posted:")::text').split(': ')[1]
item['saved_times'] = join(
'div#affix-box div:contains("Saved ")>strong::text')
item['description'] = join('div.box-item-details p ::text')
item['views'] = first(
'div#affix-box li:contains("unique views")>strong::text')
item['unique_views'] = first(
'div#affix-box li:contains("views")>strong::text')
bullets = lambda css: [
''.join(bullet.css('::text').extract()) for bullet in sel.css(css)
]
h4_bullet = 'div.box-item-details h4:contains("{}")+ul>li'.format
h3_bullet = 'div.box-item-details h3:contains("{}")+ul>li'.format
item['about_you'] = bullets(h4_bullet('About You'))
item['your_role'] = bullets(h4_bullet('Your role'))
item['requirements'] = bullets(h4_bullet('Requirements'))
item['nice_to_have'] = bullets(h4_bullet('Nice to have'))
item['why_work_with_us'] = bullets(h4_bullet('Why work with us'))
item['desired_skills'] = bullets(h3_bullet('Desired Skills'))
item['contact'] = bullets(h3_bullet('Contact Info'))
return item
def scrape_noticia(html_content):
selector = Selector(text=html_content)
url = selector.css("head link[rel=canonical]::attr(href)").get()
title = selector.css("h1#js-article-title::text").get()
timestamp = selector.css("#js-article-date::attr(datetime)").get()
writer = selector.css(".z--font-bold::text").get()
shares_count = selector.css(".tec--toolbar__item::text").get()
comments_count = selector.css(".tec--btn::attr(data-count)").get()
summary = selector.css(
".tec--article__body > p:nth-child(1) ::text").getall()
sources = selector.css(".z--mb-16 .tec--badge::text").getall()
categories = selector.css("#js-categories .tec--badge::text").getall()
if not writer:
writer = selector.css(".z--font-bold a::text").get()
if not shares_count:
shares_count = 0
else:
shares_count = str(shares_count).split()[0]
sources = [str(source).strip() for source in sources]
categories = [str(category).strip() for category in categories]
return {
"url": url,
"title": title,
"timestamp": timestamp,
"writer": str(writer).strip(),
"shares_count": int(shares_count),
"comments_count": int(comments_count),
"summary": "".join(summary),
"sources": sources,
"categories": categories,
}
def get_dilan_price(url, result_list=None, need_print=False):
try:
site_page = requests.get(url, timeout=20)
sel = Selector(site_page.text)
except Exception:
if need_print:
print("Ошибка получения по url " + url)
return None
if site_page.status_code != requests.codes.ok:
return None
# write_to_file(site_page, '/root/pricepinger_v2/dilan.txt')
# title = sel.css('title::text').extract_first().split(' -')[0]
title = sel.css('h1::text').extract_first() # .capitalize()
# price = sel.css('div.__price::text').extract_first().split()[0]
price = sel.css('div.price::text').extract_first().split()[0]
date_ts = datetime.datetime.now()
result = [title, float(price), url, 'Dilan', date_ts]
if result_list is not None:
result_list.append(result)
if need_print is True:
echo_list_to_sting(result)
return result
def detailData(self, response, **kwargs):
titleName = response.xpath('/html/body/div[2]/div[2]/div/p[2]/text()'
).extract_first() # 获取标题名字
select = Selector(response.text)
publishTime = select.css('.p2 span::text').get() # 获取时间
excelData = select.css('.Section1').getall() # 表格数据
if excelData: # 做判断，如果为表格，单独存入TXT 不是 正常存入数据
print('我是表格')
content = excelData[0]
try:
with open('./' + titleName + '.txt', 'a+',
encoding='utf-8') as f:
f.write(titleName)
f.write('\n')
f.write('\n')
f.write(publishTime)
f.write('\n')
f.write('\n')
f.write(content)
f.write('\n')
except IOError as ex:
print('写入目标文件错误，错误原因：'.ex)
else:
content = select.css('.p3 P span::text').getall()
self.writeData(titleName=titleName,
publishTime=publishTime,
content=content)
def parse_song(html: Selector):
lyrics = ''.join(
html.css(
'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div:nth-child(8)::text'
).getall()).strip()
title = html.css(
'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > b ::text'
).get()
band = html.css(
'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div.lyricsh > h2 > b ::text'
).get()[:-len(' lyrics')]
written_by = html.css(
'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div:nth-child(17) > small ::text'
).get()
if written_by:
written_by = [
author.strip()
for author in written_by[len('Writer(s): '):].split(',') if author
]
return {
'lyrics': lyrics,
'title': title,
'band': band,
'written_by': written_by,
'album': None
}
def parse_detail(self, detail_page):
"""
:param detail_page:
:return:
"""
selector = Selector(detail_page)
title = selector.css('h1 span ::text').get()
sorce = selector.xpath('//strong/text()').get()
for detail in selector.css('.indent #info'):
author = detail.xpath(
'//span[@class="pl"][text()=" 作者"]/following-sibling::a/text()'
).get()
publish_house = detail.xpath(
'//*[text()="出版社:"]/following-sibling::text()').get()
Producer = detail.xpath(
'//*[text()="出品方:"]/following-sibling::a/text()').get()
Producer_year = detail.xpath(
'//*[text()="出版年:"]/following-sibling::text()').get()
page_num = detail.xpath(
'//*[text()="页数:"]/following-sibling::text()').get()
price = detail.xpath(
'//*[text()="定价:"]/following-sibling::text()').get()
Binding = detail.xpath(
'//*[text()="装帧:"]/following-sibling::text()').get()
ISBN = detail.xpath(
'//*[text()="ISBN:"]/following-sibling::text()').get()
def song_info(html: Selector):
author_css = 'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div.lyricsh > h2 > b ::text'
lyrics = 'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div:nth-child(8) ::text'
author = html.css(author_css).get()
text = html.css(lyrics).getall()
return {'author': author, 'lyrics': ''.join(text)}
def extract_technique_synergy(sel: parsel.Selector):
if sel.css('a::attr(title)').get() == 'Temtem Types':
return None
try:
return sel.css('a::attr(title)').get().split()[0]
except AttributeError:
return None
def song_info(html: Selector):
author_css = 'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div.lyricsh > h2 > b ::text'
lyrics = 'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div:nth-child(8) ::text'
album_css = 'body > div.container.main-page > div > div.col-xs-12.col-lg-8.text-center > div.panel.songlist-panel.noprint > div.songinalbum_title > b ::text'
author = html.css(author_css).get()
text = html.css(lyrics).getall()
album = html.css(album_css).get()
def crawl_detail_page(url, title, news_type):
resp_text = requests.get(url).text
sel = Selector(resp_text)
author = sel.css('#articlewrap > div.article-info > div > a::text').extract_first() or \
sel.css('#articlewrap > div.article-info > div::text').extract_first() or ''
author = author.replace("\n", "").strip()
print(f'使用print模拟保存到数据库 {news_type} {title} {author} {url}'
) # ，实际为调用数据库插入函数，压根不需要return item出来在另外文件的地方进行保存。
def tv(canal):
response = get(f'https://meuguia.tv/programacao/canal/{canal}').text
s = Selector(response)
return {
'nome': s.css('h2::text').get(),
'inicio': s.css('div.time::text').get(),
'tipo': s.css('h3::text').get(),
}
def requestAllNames(url):
response = requests.get(defaultUrl + url)
selector = Selector(text=response.text)
titles = selector.css(".product_pod > h3 > a::text").getall()
for title in titles:
print(title)
next = selector.css(".next > a::attr(href)").get()
if (next):
return requestAllNames(next)
def get_html(title_url):
result = requests.get(title_url)
se = Selector(result.text)
title = se.css('div.content-title p::text').get()
content =se.css('div.content-title ul span::text').getall()
view_num = se.css('#views::text').get()
print(title)
print(content)
print(view_num)
def parse_trun(self, response):
# 解析比赛轮次和球队
logging.debug(response.url)
sch_trun = response.css("table.linkblock a.OddsLink").extract()
# schInfo["schedule_teams"] = schInfo["id"]
if len(sch_trun) == 0:
# 无轮次
#
scheduleInfo = copy.deepcopy(response.meta["scheduleInfoObj"])
logging.debug(scheduleInfo)
#
schInfo = ScheduleInfo()
schInfo["id"] = scheduleInfo["id"]
schInfo["area"] = scheduleInfo["area"]
schInfo["country"] = scheduleInfo["country"]
schInfo["match_name"] = scheduleInfo["match_name"]
schInfo["sch_idx"] = scheduleInfo["sch_idx"]
schInfo["sch_name"] = scheduleInfo["sch_name"]
schInfo["sch_type"] = scheduleInfo["sch_type"]
schInfo["sch_group"] = scheduleInfo["sch_group"]
schInfo["sch_trun"] = "无"
schInfo["id"] = response.meta["scheduleInfoObj"]["id"] + "_0"
schInfo["sch_url"] = response.url.replace(self.base_url, "")
yield schInfo
else:
# 有轮次
for t in sch_trun:
odds_sel = Selector(text=t)
trun_name = odds_sel.css("a::text").extract_first()
if trun_name == None or trun_name.strip() == "":
trun_name = odds_sel.css("a b::text").extract_first()
if trun_name == None or trun_name.strip() == "":
continue
trun_name = trun_name.strip()
tmp_name = trun_name.encode("utf-8")
if tmp_name == None or tmp_name == "" or tmp_name == "全部":
continue
#
scheduleInfo = copy.deepcopy(response.meta["scheduleInfoObj"])
logging.debug(scheduleInfo)
#
schInfo = ScheduleInfo()
schInfo["id"] = scheduleInfo["id"]
schInfo["area"] = scheduleInfo["area"]
schInfo["country"] = scheduleInfo["country"]
schInfo["match_name"] = scheduleInfo["match_name"]
schInfo["sch_idx"] = scheduleInfo["sch_idx"]
schInfo["sch_name"] = scheduleInfo["sch_name"]
schInfo["sch_type"] = scheduleInfo["sch_type"]
schInfo["sch_group"] = scheduleInfo["sch_group"]
schInfo["sch_trun"] = trun_name
schInfo["id"] = response.meta["scheduleInfoObj"][
"id"] + "_" + trun_name
schInfo["sch_url"] = odds_sel.xpath(
"//@href").extract_first().strip()
yield schInfo
def parse_article(self, url, html) -> dict:
"""Parse html for data"""
sel = Selector(text=html)
data = {
'url': url,
'date': sel.css('time::attr(datetime)').extract_first(),
'title': sel.css('h1 ::text').extract_first(),
}
return data
def _get_item(self, entry: Selector):
video_id = entry.css('videoId::text').get()
return PodcastItem(
item_id=video_id,
title=entry.css('title::text').get(),
description=entry.css('description::text').get(),
date=datetime.fromisoformat(entry.css('published::text').get()),
image=entry.css('group > thumbnail::attr(url)').get(),
content_type="video/mp4",
)
def scrape_noticia(html_content):
selector = Selector(text=html_content)
url = selector.css("meta[property='og:url']::attr(content)").get()
title = selector.css("h1#js-article-title::text").get()
timestamp = selector.css("#js-article-date::attr(datetime)").get()
writer = selector.css("a.tec--author__info__link::text").get()
shares_count = selector.css("div.tec--toolbar__item::text").re_first(
r"\d+")
comments_count = selector.css("#js-comments-btn::text").re_first(r"\d+")
summary = "".join(
selector.css(".tec--article__body > p:first-child *::text").getall())
sources = selector.css("div.z--mb-16 .tec--badge::text").getall()
categories = selector.css("#js-categories a.tec--badge::text").getall()
return {
"url":
url,
"title":
title,
"timestamp":
timestamp,
"writer":
writer.strip() if writer else writer,
"shares_count": (int(shares_count) if shares_count else 0),
"comments_count": (int(comments_count) if comments_count else 0),
"summary":
summary,
"sources":
[source.strip() for source in sources] if sources else sources,
"categories":
[categorie.strip()
for categorie in categories] if categories else categories,
}
def parse(html):
document = Selector(text=html)
memes = [
catch_errors(parse_meme, element)
for element in document.css("main .media-element")
]
memes = [meme for meme in memes if meme is not None]
title = document.css("title::text").get()
next_page_url = "/kwejk/page/" + get_last_part_url(
document.css(".btn-next::attr(href)").get())
return Page(title, memes, next_page_url)
def download_one(url):
response = requests.get(url,timeout=40)
response.raise_for_status()
response.encoding="gbk"
sel=Selector(response.text)
title=sel.css('em::text').get()
f=open(title+'.txt',mode='w',encoding='gbk')
f.write(title)
for list in sel.css('#content::text').getall():
print(list.strip(),file=f)
f.close()
def parse(html):
document = Selector(text=html)
memes = [
catch_errors(parse_meme, element) for element in document.css("article.story")
]
memes = [meme for meme in memes if meme is not None]
title = document.css("title::text").get()
next_page_url = "/anonimowe/page/" + find_id_in_url(
document.css("nav.pagination > div.next > a::attr(href)").get()
)
return Page(title, memes, next_page_url)
def parse(self, response):
sel = Selector(text=response.body.decode('utf-8'))
products = sel.css('.product__title::attr(href)').extract()
yield \
merge({'products': products}, \
pick(['status', '_url'], \
vars(response)))
url = sel.css('.js-next::attr(href)').extract_first()
if url:
req = sub(r'\?.*', '', response.request.url) + url
yield Request(req, callback=self.parse)
def parse(html):
document = Selector(text=html)
memes = [
catch_errors(parse_meme, element)
for element in document.css(".demotivator")
]
memes = [meme for meme in memes if meme is not None]
title = document.css("title::text").get()
next_page_url = "/demotywatory/page/" + get_last_part_url(
document.css("a.next-page::attr(href)").get())
return Page(title, memes, next_page_url)
async def test_stop(test_client):
agent = Agent("jid@server", "password")
agent.web.setup_routes()
client = await test_client(agent.web.app)
response = await client.get("/spade/stop")
response = await response.text()
sel = Selector(text=response)
assert sel.css("div.alert-warning > span::text").get().strip() == "Agent is stopping now."
with LogCapture() as log:
try:
await client.get("/spade/stop/now/", timeout=0.0005)
except requests.exceptions.ReadTimeout:
pass
log.check_present(('spade.Web', 'WARNING', "Stopping agent from web interface."))
counter = 5
while agent.is_alive() and counter > 0:
counter -= 0.5
time.sleep(0.5)
assert not agent.is_alive()
async def test_request_home(test_client):
agent = make_connected_agent("jid@server", "password")
future = agent.start(auto_register=False)
future.result()
agent.web.setup_routes()
client = await test_client(agent.web.app)
response = await client.get("/spade")
response = await response.text()
sel = Selector(text=response)
assert sel.css("title::text").get() == "jid agent"
assert sel.css("img::attr(src)").get() == agent.avatar
assert sel.css("ul.products-list > li").getall() == []
agent.stop()
def getheaders():
'从网页源代码内解析出 uuid与Xsrftoken'
z1 = s.get('https://www.zhihu.com/')
sel = Selector(z1.text)
jsdata = sel.css('div#data::attr(data-state)').extract_first()
xudid = json.loads(jsdata)['token']['xUDID']
xsrf = json.loads(jsdata)['token']['xsrf']
headers = headers_raw_to_dict(post_headers_raw)
headers['X-UDID'] = xudid
headers['X-Xsrftoken'] = xsrf
return headers
def load_chapters(url):
"""
Loads all chapters from a manga comic and returns a list for dictionaries
with related data.
:return: chapter list in asc order
"""
text = requests.get(url).text
sel = Selector(text)
hel_gen = sel.css(".chlist h3, .chlist h4")
chapter_gen = map(hel_to_chapter, hel_gen)
available_chapter_gen = filter(lambda v: v['title'], chapter_gen)
return reversed(list(available_chapter_gen))
async def test_add_get(test_client):
agent = Agent("jid@server", "password")
agent.web.add_get("/test", lambda request: {"number": 42}, "examples/hello.html")
agent.web.setup_routes()
client = await test_client(agent.web.app)
response = await client.get("/test")
response = await response.text()
sel = Selector(text=response)
assert sel.css("h1::text").get().strip() == "42"
agent.stop()
def main(argv=None, progname=None):
parser = argparse.ArgumentParser(prog=progname, description=__doc__)
parser.add_argument('expr', metavar='EXPRESSION',
help="A CSSexpression, or a XPath expression if --xpath is given.")
parser.add_argument('file', metavar='FILE', nargs='?',
help="If missing, it reads the HTML content from the standard input.")
parser.add_argument('--xpath', action='store_true',
help="Given expression is a XPath expression.")
parser.add_argument('--re', metavar='PATTERN',
help="Apply given regular expression.")
parser.add_argument('--encoding', metavar='ENCODING', default='utf-8',
help="Input encoding. Default: utf-8.")
parser.add_argument('--repr', action='store_true',
help="Output result object representation instead of as text.")
# TODO: Output this and parsel version.
args = parser.parse_args(argv)
if args.file:
text = open(args.file).read()
else:
text = sys.stdin.read()
if isinstance(text, six.binary_type):
try:
text = text.decode(args.encoding)
except UnicodeDecodeError:
parser.error("Failed to decode input using encoding: %s" % args.encoding)
sel = Selector(text=text)
if args.xpath:
result = sel.xpath(args.expr)
else:
result = sel.css(args.expr)
if args.re:
regex = args.re.encode(args.encoding)
regex = regex.decode('string_escape' if six.PY2 else 'unicode_escape')
out = result.re(re.compile(regex, re.IGNORECASE | re.UNICODE))
else:
out = result.extract()
if args.repr:
pprint.pprint(out)
else:
print("\n".join(out))
return 0
def get_alexa_demographics(url, db_session=False):
if db_session is not False:
result = list(db_session.query(WebsitesCache).filter_by(link=url))
if len(result) > 0 and result[0].male_ratio_alexa >= 0:
return float(result[0].male_ratio_alexa), float(result[0].female_ratio_alexa)
else:
return 0.0, 0.0
orig_url = url
url = "http://www.alexa.com/siteinfo/" + url
response = requests.get(url)
# We need the decode part because Selector expects unicode.
selector = Selector(response.content.decode('utf-8'))
bars = selector.css("#demographics-content .demo-col1 .pybar-bg")
values = []
for bar in bars:
value = bar.css("span::attr(style)").extract()[0]
value = int(re.search(r'\d+', value).group())
values.append(value)
male_ratio = 0.0
female_ratio = 0.0
if sum(values) == 0:
print "No alexa rating for " + url
else:
male_ratio = float(values[0] + values[1]) / sum(values)
female_ratio = float(values[2] + values[3]) / sum(values)
print url
print values
print male_ratio, female_ratio
# Do we want to cache the result?
if db_session is not False:
try:
db_session.query(WebsitesCache).filter(WebsitesCache.link==orig_url) \
.update({
'male_ratio_alexa': male_ratio,
'female_ratio_alexa': female_ratio
})
db_session.commit()
except:
print "Could not update " + url
return male_ratio, female_ratio
async def test_get_messages(test_client):
agent = Agent("jid@server", "password")
agent.web.setup_routes()
client = await test_client(agent.web.app)
# add messages to trace
for i in range(5):
msg = Message(body=str(i), sender="{}@server".format(i), to="receiver@server")
agent.traces.append(msg)
response = await client.get("/spade/messages/")
response = await response.text()
sel = Selector(text=response)
assert len(sel.css("ul.timeline > li").getall()) == 6 # num messages + end clock
agent.stop()
def download_chapter(chapter, folder_name):
"""
Grabs all images from a chapter and writes them down to filesystem.
"""
folder_name = werkzeug.utils.secure_filename(folder_name)
# if the folder does not exist ...
if not os.path.exists(folder_name):
os.mkdir(folder_name)
text = requests.get(chapter['href']).text
sel = Selector(text)
for value in sel.css("select[class='m'] > option::attr(value)").extract():
value = int(value)
url = re.sub(r'\d+\.html', '%d.html' % value, chapter['href'])
download_page(url, folder_name)
async def test_get_behaviour(test_client):
class EmptyOneShotBehaviour(OneShotBehaviour):
async def run(self):
self.kill()
agent = Agent("jid@server", "password")
behaviour = EmptyOneShotBehaviour()
agent.add_behaviour(behaviour)
agent.web.setup_routes()
client = await test_client(agent.web.app)
response = await client.get("/spade/behaviour/OneShotBehaviour/EmptyOneShotBehaviour/")
response = await response.text()
sel = Selector(text=response)
assert sel.css("section.content-header > h1::text").get().strip() == "OneShotBehaviour/EmptyOneShotBehaviour"
agent.stop()
async def test_add_post(test_client):
agent = Agent("jid@server", "password")
async def handle_post(request):
form = await request.post()
number = form["number"]
return {"number": number}
agent.web.add_post("/test", handle_post, "examples/hello.html")
agent.web.setup_routes()
client = await test_client(agent.web.app)
response = await client.post("/test", data={"number": 1024})
response = await response.text()
sel = Selector(text=response)
assert sel.css("h1::text").get() == "1024"
agent.stop()
def download_page(url, folder_name):
text = requests.get(url).text
sel = Selector(text)
for src in sel.css("img[id='image']::attr(src)").extract():
basename = os.path.basename(src)
safe_basename = werkzeug.utils.secure_filename(basename)
filename = os.path.join(folder_name, safe_basename)
filename = os.path.abspath(filename)
# file is not there or has a invalid size ...
if not os.path.exists(filename) or os.path.getsize(filename) == 0:
data = requests.get(src).content
with open(filename, 'wb') as file:
file.write(data)
print('{0} written.'.format(filename))
else:
print('{0} exists. Skipping.'.format(filename))
def _find_match(self, sel: Selector) -> Match:
xpath = lambda x: sel.xpath(x).extract_first(default='').strip()
item = Match()
item['url'] = urljoin(self.url_base, xpath(".//a/@href"))
item['id'] = (re.findall('matches/(\d+)', item['url']) or [None])[0]
item['game'] = next((g for g in self.games if g in item['url'].lower()))
item['time'] = xpath("td[@class='status']/span/text()")
item['time_secs'] = time_to_seconds(item['time'])
item['timestamp'] = int((datetime.now() + timedelta(item['time_secs'])).timestamp())
item['t1'] = xpath(".//span[contains(@class,'opp1')]/span/text()")
item['t1_country'] = xpath(".//span[contains(@class,'opp1')]/span[contains(@class,'flag')]/@title")
item['t1_country_short'] = xpath(".//span[contains(@class,'opp1')]"
"/span[contains(@class,'flag')]/@class").split()[-1]
item['t2'] = xpath(".//span[contains(@class,'opp2')]/span/text()")
item['t2_country'] = xpath(".//span[contains(@class,'opp2')]/span[contains(@class,'flag')]/@title")
item['t2_country_short'] = xpath(".//span[contains(@class,'opp2')]"
"/span[contains(@class,'flag')]/@class").split()[-1]
scores = sel.css('.score::text').extract()
item['t1_score'] = scores[0] if scores else None
item['t2_score'] = scores[1] if len(scores) > 1 else None
return item
async def test_get_agent(test_client):
agent = make_presence_connected_agent("jid@server", "password")
future = agent.start(auto_register=False)
future.result()
agent.web.setup_routes()
client = await test_client(agent.web.app)
jid = "friend@server"
item = Item(jid=JID.fromstr(jid))
agent.presence.roster._update_entry(item)
response = await client.get(f"/spade/agent/{jid}/")
response = await response.text()
sel = Selector(text=response)
assert sel.css("section.content-header > h1::text").get().strip() == jid
agent.stop()
def search_command(value):
url = "{domain}/search.php?".format(domain=domain)
quote = urllib.parse.quote(value)
query = {
'name': quote,
'name_method': 'cw',
'author': '',
'author_method': 'cw',
'artist': '',
'artist_method': 'cw',
'is_complete': '',
'type': '',
'advopts': '1',
'rating': '',
'rating_method': 'eq',
'released': '',
'released_method': 'eq',
'genres[Sci-fi]': '0',
'genres[Horror]': '0',
'genres[Sports]': '0',
'genres[Action]': '0',
'genres[Shoujo Ai]#': '0',
'genres[Drama]': '0',
'genres[Fantasy]': '0',
'genres[Mystery]': '0',
'genres[Gender Bender]': '0',
'genres[One Shot]': '0',
'genres[Psychological]': '0',
'genres[Tragedy]': '0',
'genres[Historical]': '0',
'genres[Mecha]': '0',
'genres[Yuri]': '0',
'genres[Seinen]': '0',
'genres[Adult]': '0',
'genres[Slice of Life]': '0',
'genres[Doujinshi]': '0',
'genres[Romance]': '0',
'genres[School Life]': '0',
'genres[Comedy]': '0',
'genres[Shoujo]': '0',
'genres[Ecchi]': '0',
'#genres[Harem]': '0',
'genres[Smut]': '0',
'genres[Yaoi]': '0',
'genres[Shounen Ai]': '0',
'genres[Martial Arts]': '0',
'genres[Josei]': '0',
'genres[Shounen]': '0',
'genres[Mature]': '0',
'genres[Webtoons]': '0',
'genres[Supernatural]': '0',
'genres[Adventure]': '0',
}
url += urllib.parse.urlencode(query)
try:
data = requests.get(url).text
except urllib.error.URLError:
# mangafox requires a 5 seconds delay
# between searches
import time
time.sleep(5)
data = requests.get(url).text
sel = Selector(data)
results = list()
for link in sel.css('td:first-child > a:first-child'):
manga_url = link.css('::attr(href)').extract_first()
name = manga_url[7:].split('/')[2]
results.append(odict([
('title', link.css('::text').extract_first()),
('name', "%s (use for download)" % name),
('url', manga_url),
]))
if len(results):
print("")
for manga in results:
for key, value in manga.items():
print("%s: %s" % (key, value))
print("")
else:
print('No results found')
with open('lamberti.json') as jsonfile:
jsondata = json.load(jsonfile)
with open('lamberti.geojson') as geojsonfile:
geojsondata = json.load(geojsonfile)
for booth in jsondata:
booth_no = int(booth['nr'][-2:])
r = requests.get(booth['url'])
if r.status_code == 200:
text = r.text
selector = Selector(text=text)
booth_name = selector.css('.booth-title::text').get()
booth_descr = selector.css('.booth-body > p::text').getall()
if isinstance(booth_descr, list):
booth_descr = " ".join(booth_descr)
booth_owner_company = selector.css(
'.contactParticle--company::text').get()
booth_owner_name = selector.css(
'.contactParticle--name\:firstname\,lastname::text').get()
booth_owner_street = selector.css(
'.contactParticle--street::text').get()
booth_owner_city = selector.css(
'.contactParticle--city\:postal_code\,locality::text').get()
booth_owner_phone = selector.css('.contactParticle--phone::text').get()
booth_owner_email = selector.css(
